CN113435547A - Water quality index fusion data anomaly detection method and system - Google Patents
Water quality index fusion data anomaly detection method and system Download PDFInfo
- Publication number
- CN113435547A CN113435547A CN202110992212.2A CN202110992212A CN113435547A CN 113435547 A CN113435547 A CN 113435547A CN 202110992212 A CN202110992212 A CN 202110992212A CN 113435547 A CN113435547 A CN 113435547A
- Authority
- CN
- China
- Prior art keywords
- data
- index
- water quality
- abnormal
- detection model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 214
- 238000001514 detection method Methods 0.000 title claims abstract description 89
- 230000004927 fusion Effects 0.000 title claims abstract description 58
- 230000002159 abnormal effect Effects 0.000 claims abstract description 153
- 238000012544 monitoring process Methods 0.000 claims abstract description 83
- 238000000034 method Methods 0.000 claims abstract description 39
- 230000005856 abnormality Effects 0.000 claims abstract description 34
- 238000011156 evaluation Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000012417 linear regression Methods 0.000 claims description 9
- 230000006866 deterioration Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 description 4
- 241000894006 Bacteria Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 239000002352 surface water Substances 0.000 description 2
- VYZAMTAEIAYCRO-UHFFFAOYSA-N Chromium Chemical compound [Cr] VYZAMTAEIAYCRO-UHFFFAOYSA-N 0.000 description 1
- 241001061260 Emmelichthys struhsakeri Species 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 239000003513 alkali Substances 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 231100000357 carcinogen Toxicity 0.000 description 1
- 239000003183 carcinogenic agent Substances 0.000 description 1
- 229910052804 chromium Inorganic materials 0.000 description 1
- 239000011651 chromium Substances 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 150000002222 fluorine compounds Chemical class 0.000 description 1
- 229910001385 heavy metal Inorganic materials 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000002906 microbiologic effect Effects 0.000 description 1
- 150000002825 nitriles Chemical class 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 150000002989 phenols Chemical class 0.000 description 1
- 125000005575 polycyclic aromatic hydrocarbon group Chemical group 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 150000003568 thioethers Chemical class 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application provides a water quality index fusion data abnormity detection method and a system, and the method comprises the following steps: acquiring historical fusion data of water quality monitoring and monitoring data of a water quality automatic station at the current moment; establishing a full-index isolated forest detection model, a correlation index abnormity detection model and a single-index abnormity detection model according to the acquired water quality monitoring history fusion data; inputting the acquired monitoring data of the water quality automatic station at the current moment into the established full-index isolated forest detection model, the established associated index abnormality detection model and the established single-index abnormality detection model, and respectively outputting first abnormal data, second abnormal data and third abnormal data; and evaluating the water quality at the current moment according to the first abnormal data, the second abnormal data and the third abnormal data, and calculating the total evaluation value of the water area to be evaluated for the water quality badness. The method and the device perform abnormal value detection on multi-level water quality index data and evaluate the current water quality condition and water quality improvement condition.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a water quality index fusion data abnormity detection method and system.
Background
At present, an algorithm for detecting abnormal values of water quality data mainly uses an extreme value analysis method based on a statistical principle, supposes that the water quality data meets normal distribution, uses an extreme value analysis method such as a triple standard deviation method, a quartile judgment method, a fixed threshold value method and the like to respectively calculate a reasonable interval for each index, and determines the data as an abnormal value when the upper limit of the interval is exceeded or the lower limit of the interval is fallen below, thereby screening the abnormal values in a data sequence.
The extreme value analysis-based method is used for monitoring abnormal values of data of a single water quality index, and the analysis method is only suitable for the situation that the data distribution is approximate to normal distribution. However, in terms of the water quality index data, because the data exhibits periodicity and trend, the distribution is mostly irregular skewed distribution or multimodal distribution, and the application of the method can lead to that the normal water quality data is regarded as abnormal values or that the abnormal values are regarded as normal values. In addition, many water quality indexes in the water environment are correlated, abnormal value detection is performed only on single index data, abnormal information generated by data index combination cannot be found, and in addition, the current water quality condition and the water quality improvement condition need to be evaluated to provide powerful support for water quality regulation.
Disclosure of Invention
The application aims to provide a water quality index fusion data anomaly detection method and system, which are used for carrying out anomaly value detection on multi-level water quality index data such as a full index, a correlation index, a single index and the like, detecting the anomaly data, pre-judging the deterioration of a water environment in advance, ensuring the objective authenticity of water environment quality monitoring data, providing data decision support for water environment management work, evaluating the current water quality condition and the water quality improvement condition and providing powerful support for water quality regulation.
In order to achieve the above object, the present application provides a method for detecting abnormality of water quality index fusion data, comprising the steps of: acquiring historical fusion data of water quality monitoring and monitoring data of a water quality automatic station at the current moment; establishing a full-index isolated forest detection model, a correlation index abnormity detection model and a single-index abnormity detection model according to the acquired water quality monitoring history fusion data; inputting the acquired monitoring data of the water quality automatic station at the current moment into the established full-index isolated forest detection model, the established associated index abnormality detection model and the established single-index abnormality detection model, and respectively outputting first abnormal data, second abnormal data and third abnormal data; and evaluating the water quality at the current moment according to the first abnormal data, the second abnormal data and the third abnormal data, and calculating the total evaluation value of the water area to be evaluated for the water quality badness.
As above, wherein, the method for detecting the abnormality of the water quality index fusion data further comprises the following steps: and evaluating the water quality improvement condition of the water area to be evaluated according to the first abnormal data, the second abnormal data and the third abnormal data, and calculating the water quality improvement value of the water area to be evaluated.
The method for establishing the full-index isolated forest detection model according to the acquired historical fusion data of water quality monitoring comprises the following steps of: selecting from historical fusion data of water quality monitoring
Taking the full index sample data as a subdata set, and putting the subdata set into a root node of an isolated tree; wherein, height limit is set for the isolated tree; randomly selecting an index data in the subdata set and randomly generating a cutting point
(ii) a Less than cutting point in currently selected index data
Is placed in the left branch of the current node and is greater than or equal to the cut point
The point of (2) is placed at the right branch of the current node to form a new leaf node; and continuously constructing new leaf nodes at the left branch node and the right branch node until only one index data is arranged on the leaf nodes, all the characteristics of the index data on the nodes are the same or the isolated tree grows to the set height limit.
As above, the method for establishing the full-index isolated forest detection model further comprises the following steps: and calculating the abnormal scores of all full index sample data in the solitary forest.
The method for calculating the abnormal scores of all the full index sample data in the solitary forest comprises the following steps of calculating the average path length of a single solitary tree; calculating full index sample data according to the average path length of single isolated tree
The abnormality score of (1).
The method as above, wherein the full index sample data
The anomaly score calculation formula of (2) is:
wherein,
sample data representing full index
An abnormality score of (a);
sample data representing full index
Path length expectation in solitary forests;
sample data representing full index
The path length of (a); the path length is the number of edges that pass from the root node to the leaf nodes of the isolated tree.
As above, the method for establishing the correlation index abnormality detection model according to the historical fusion data of water quality monitoring includes the following steps: selecting a related index data set from the historical fusion data of water quality monitoring; and establishing a correlation index abnormity detection model according to the correlation index data set.
As above, wherein, according to the associated index data set, the establishing of the associated index abnormality detection model includes the following sub-steps: calculating automatic station sample points
Distance to all other automation station sample points; calculating automatic station sample points
To (1) a
Distance between two adjacent plates
；
Representing automatic station sample points
And an automated station sample site
The distance of (d); obtaining all automated station sample points
To (1) a
Distance neighborhood
(ii) a First, the
Including sample points in the proximity of the robotic station
Is not more than the distance of
All of the automated station sample points of distance; calculating automatic station sample points
The reachable distance of (a); according to the automatic station sample point
Calculating the local reachable density of all the automatic station sample points; calculating automatically from the local achievable densityLocal outlier factors for station sample points.
The method for establishing the single-index dynamic threshold model according to the historical fusion data of water quality monitoring comprises the following steps: selecting single index sample data from the historical fusion data of water quality monitoring; defining index data time series of single index sample data as
The number of times is defined as
Establishing a linear regression model according to the index data time sequence; and calculating the dynamic threshold interval of the index data at the next moment according to the linear regression model.
The application still provides a quality of water index fuses data anomaly detection system, its characterized in that, this system includes: the data acquisition device is used for acquiring historical fusion data of water quality monitoring and monitoring data of the water quality automatic station at the current moment; the model establishing module is used for establishing a full-index isolated forest detection model, a correlation index abnormity detection model and a single-index abnormity detection model according to the acquired historical fusion data of water quality monitoring; the abnormal data acquisition module is used for inputting the acquired monitoring data of the water quality automatic station at the current moment into the established full-index isolated forest detection model, the established associated index abnormal detection model and the established single-index abnormal detection model, and respectively acquiring first abnormal data, second abnormal data and third abnormal data; and the data processor is used for evaluating the water quality at the current moment according to the first abnormal data, the second abnormal data and the third abnormal data and calculating the total evaluation value of the water area to be evaluated for the water quality deterioration.
The beneficial effect that this application realized is as follows:
(1) according to the method, a set of multi-level abnormal value detection method aiming at multiple indexes, related indexes and single index is established, the abnormal value detection accuracy in the surface water environment monitoring data is effectively improved, the false detection rate and the missing detection rate of abnormal value detection are reduced, the authenticity and the objectivity of the monitoring data are guaranteed, and meanwhile, data support is provided for finding out that the water environment is about to deteriorate in advance.
(2) According to the method and the device, the water quality of the water area to be evaluated and the water quality improvement condition are evaluated according to the acquired first abnormal data, second abnormal data and third abnormal data, so that the water quality condition is comprehensively evaluated, whether the water quality condition of the current water quality to be evaluated meets the functional application of the water area to be evaluated is judged according to the functional application of the water area to be evaluated, whether the water quality improvement meets the requirement is judged according to the water quality improvement condition, and the water quality condition is better managed.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art according to the drawings.
Fig. 1 is a flowchart of a water quality index fusion data anomaly detection method according to an embodiment of the present application.
Fig. 2 is a flowchart of a method for establishing a full-index isolated forest detection model according to an embodiment of the application.
Fig. 3 is a flowchart of a method for establishing an association index anomaly detection model according to an embodiment of the present application.
Fig. 4 is a flowchart of a method for selecting a correlation index data set according to an embodiment of the present application.
Fig. 5 is a schematic structural diagram of a water quality index fusion data anomaly detection system according to an embodiment of the present application.
Reference numerals: 10-a data acquisition device; 20-a model building module; 30-an abnormal data acquisition module; 40-a data processor; 100-water quality index fusion data abnormity detection system.
Detailed Description
The technical solutions in the embodiments of the present application are clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Example one
As shown in fig. 1, the present application provides a method for detecting abnormality of water quality index fusion data, which comprises the following steps:
and step S1, acquiring historical fusion data of water quality monitoring and current-time water quality automatic station monitoring data.
The historical fusion data of water quality monitoring comprises historical water quality automatic station monitoring data and historical manual water quality index acquisition data. The historical water quality automatic station monitoring data is data for automatically monitoring water quality by adopting automatic water quality monitoring equipment; the historical manual water quality index acquisition data is data acquired by manually acquiring water quality.
And step S2, establishing a full-index isolated forest detection model, a correlation index abnormity detection model and a single-index abnormity detection model according to the acquired historical fusion data of water quality monitoring.
Specifically, a full-index isolated forest model is established according to full-index data of historical fusion data of water quality monitoring, the full-index data comprises all data of multiple indexes, and for example, the full-index data is a set of 9 index data. The index data includes: lead, chromium and other heavy metal content, chemical indicators (e.g., physical indicators such as water temperature, suspended matter, turbidity, transparency, and conductivity, PH, total alkali (acid) content, and total hardness), dissolved oxygen content, other harmful substances (e.g., volatile phenols, cyanides, oils, fluorides, sulfides, and carcinogens such as organic pesticides and polycyclic aromatic hydrocarbons), and microbiological indicators (e.g., total bacteria, coliform bacteria, etc.).
As shown in fig. 2, as a specific embodiment of the present invention, the method for establishing a full-index isolated forest detection model according to the acquired historical fusion data of water quality monitoring includes the following steps:
step S210, selecting from the historical fusion data of water quality monitoring
And taking the full index sample data as a subdata set, and putting the subdata set into a root node of an isolated tree.
Preferably, the height of the orphan tree is limited to
(ii) a Wherein,
represents a height;
represents a maximum height function;
and the total number of the selected full index sample data is represented.
The sub data set comprises a plurality of full index data, and each full index data comprises a plurality of index data.
Step S220, randomly selecting an index data in the subdata set, and randomly generating a cutting point
。
Specifically, a cutting point is randomly generated in the data range of the current isolated tree node
And the cutting point is the number between the maximum value and the minimum value of the index data in the current sub data set.
Step S230, the index data selected currently is smaller than the cutting point
Is placed in the left branch of the current node and is greater than or equal to the cut point
Is placed in the right branch of the current node to form a new leaf node.
Step S240, recursion steps S220 and S230 are carried out on the left branch node and the right branch node, new leaf nodes are continuously constructed until only one index data on the leaf nodes and all characteristics of the index data on the nodes are the same or the isolated tree grows to the set height limit
。
And step S250, calculating the abnormal scores of all full index sample data in the solitary forest.
Step S250 includes the following substeps:
in step S251, the average path length of a single isolated tree is calculated.
Specifically, the calculation formula of the average path length of a single isolated tree is as follows:
wherein,
representing the average path length of the isolated tree;
representing the sum of the tones, whose value is equal to
；
And the total number of the selected full index sample data is represented.
Step S252, according to the average path length of the single isolated tree, an abnormality score of the full index sample data is calculated.
Specifically, full index sample data
The anomaly score calculation formula of (2) is:
wherein,
sample data representing full index
An abnormality score of (a);
sample data representing full index
Path length expectation in solitary forests;
sample data representing full index
The path length of (a); the path length is the number of edges that pass from the root node to the leaf nodes of the isolated tree.
As shown in fig. 3, as a specific embodiment of the present invention, the method for establishing an abnormal detection model of a correlation index according to the historical fusion data of water quality monitoring includes the following steps:
step S310, selecting a related index data set from the water quality monitoring historical fusion data.
As shown in fig. 4, step S310 includes the following sub-steps:
and step S311, selecting the manual water quality index acquisition data of the water quality monitoring station in the last year from the historical water quality monitoring fusion data.
And step S312, initializing each manual water quality index acquisition data to form a new index sequence.
And step S313, calculating the gray correlation degree among all the manual water quality index collected data by adopting a gray correlation method.
And step S314, selecting the manual water quality index acquisition data with the grey correlation degree larger than 0.6 as the manual water quality correlation index data.
Step S315, according to the manual water quality related index data, water quality automatic station monitoring data of related indexes corresponding to each manual water quality related index data are obtained, and a data set is formed and serves as a related index data set.
Step S320, establishing a correlation index abnormity detection model according to the correlation index data set.
Step S320 includes the following substeps:
step S321, calculating sample points of the automatic station
Distance to all other automation station sample points. For example: and selecting a Euclidean distance calculation method.
Wherein, the automatic station sample point refers to the sample data of the monitoring data of the water quality automatic station.
Step S322, calculating the sample point of the automatic station
To (1) a
Distance between two adjacent plates
And the following conditions are satisfied:
at least no automatic station sample points are included in the set
In which
Dot
Satisfy the following requirements
；
At most, there are no more than automatic station sample points in the set
In which
Dot
Satisfy the following requirements
。
Step S323, all automatic station sample points are obtained
To (1) a
Distance neighborhood
The first is
Including sample points in the proximity of the robotic station
Is not more than the distance of
All robotic station sample points of distance.
Step S324, calculating the sample points of the automatic station
Reach distance of, sample points of the automated station
And an automated station sample site
Is defined as:
wherein,reach-d k (p,o)representing automatic station sample points
And an automated station sample site
The reachable distance of (a); max { } denotes taking the maximum value;d k (o) Representing automatic station sample points
To (1) a
A distance;d(p,o) Representing automatic station sample points
And an automated station sample site
The actual distance of (c).
Step S325, calculate the local reachable density of all the automatic station sample points according to the reachable distance of the automatic station sample points.
The local reachable density calculation formula of the sample points of the automatic station is as follows:
wherein,
representing a local achievable density of the automated station sample points;
representing automatic station sample points
To (1) a
A distance neighborhood;reach-d k (p,o)representing automatic station sample points
And an automated station sample site
Is reached.
In step S326, the local outlier factor of the sample point of the automatic station is calculated according to the local reachable density.
The calculation formula of the local outlier factor of the sample point of the automatic station is as follows:
wherein,
a local outlier factor representing an automatic station sample point;
representing automatic station sample points
To (1) a
A distance neighborhood;
representing automatic station sample points
Local achievable density of;
representing the locally achievable density of the sample points of the automated station.
If the local outlier factor is closer to 1, the automatic station sample point is indicated
Sample points of the automatic station with similar density to its neighborhood points
Possibly in the same cluster as its neighbourhood; if the local outlier factor is less than 1, the automatic station sample point is indicated
Is higher than the density of its neighborhood points, the sample points of the automatic station
Are dense points; if the local outlier factor is greater than 1, the automatic station sample point is indicated
Is less than its neighborhood point density, the sample points of the rover station
The more likely it is an outlier.
As a specific embodiment of the invention, the method for establishing the single-index dynamic threshold model according to the historical fusion data of water quality monitoring comprises the following steps:
and T1, selecting single index sample data from the historical fusion data of water quality monitoring.
Specifically, abnormal data in the historical fusion data of water quality monitoring are removed, and single index sample data is selected.
Step T1 includes the following steps:
and T110, calculating the average value of the first 12 pieces of manual water quality index acquisition data of the current section as first average value data aiming at each index data.
And step T120, calculating the average value of the monitoring data of the automatic water quality station in the previous three months as first sliding average value data and the average value of the monitoring data of the automatic water quality station in the previous month as second sliding average value data based on the monitoring data of the automatic water quality station.
Specifically, water quality automatic station monitoring data of the first three months after abnormal data are removed are obtained, and the average value of the obtained water quality automatic station monitoring data of the first three months is calculated and used as first sliding average value data; and acquiring the monitoring data of the automatic water quality station in the previous month after the abnormal data are removed, and calculating the average value of the acquired monitoring data of the automatic water quality station in the previous month as second sliding average value data.
And T130, combining the obtained first mean value data, the first sliding mean value data and the second sliding mean value data with index data at a plurality of moments before the current moment (preferably, 6 moments before the current moment) to form an index data time sequence of each index, and using the index data time sequence as single index sample data.
The index data time series includes index data at a plurality of time instants.
Step T2, defining the index data time series of single index sample data as
The number of times is defined as
And establishing a linear regression model according to the index data time series.
Linear regression modelComprises the following steps:
；
wherein,ifor the purpose of the index identification,
the number of moments;
time-series index data
And the number of times
Inputting into a linear regression model to obtainaAndbthe numerical value of (c).
Step T3, calculating the dynamic threshold interval of the index data at the next moment according to the linear regression model
。
Specifically, the calculation formula of the dynamic threshold interval is as follows:
wherein,
is the calculated value of the linear regression model at the next moment,
index data of the next moment;
the standard deviation is indicated.
And step S3, inputting the acquired monitoring data of the water quality automatic station at the current moment into the established full-index isolated forest detection model, the established associated index abnormality detection model and the established single-index abnormality detection model, and respectively outputting first abnormal data, second abnormal data and third abnormal data.
As a specific embodiment of the present invention, a method for acquiring first abnormal data includes:
inputting the monitoring data of the automatic water quality station at the current moment into a full-index isolated forest detection model, calculating the distance between the monitoring data of the automatic water quality station at the current moment and all historical full-index sample data by adopting an Euclidean distance calculation formula, acquiring the abnormal score of the sample data closest to the current moment, taking the abnormal score of the sample data closest to the current moment as the abnormal score of the monitoring data of the automatic water quality station at the current moment, and if the abnormal score of the monitoring data of the automatic water quality station at the current moment is close to 1, regarding the monitoring data of the automatic water quality station at the current moment as first abnormal data, otherwise, regarding the monitoring data of the automatic water quality station as normal data.
As a specific embodiment of the present invention, the method for acquiring the second abnormal data includes:
and inputting the monitoring data of the automatic water quality station at the current moment into a correlation index abnormality detection model, calculating a local outlier factor of the sample point of the automatic station, and if the local outlier factor of the sample point of the automatic station exceeds a preset threshold, defining the data of the sample point of the automatic station as second abnormal data, otherwise, defining the data as normal data.
As a specific embodiment of the present invention, the method of acquiring the third exception data is:
inputting the monitoring data of the automatic water quality station at the current moment into a single-index abnormity detection model, and if the index data of the monitoring data of the automatic water quality station at the current moment
Out of the dynamic threshold interval
And in the internal time, defining the index data of the monitoring data of the water quality automatic station at the current moment as third abnormal data, and otherwise, defining the index data as normal data.
And step S4, evaluating the water quality at the current moment according to the first abnormal data, the second abnormal data and the third abnormal data, and calculating the total evaluation score of the water area to be evaluated for water quality badness.
Step S4 includes the following sub-steps:
step S410, acquiring first abnormal data, second abnormal data and third abnormal data of data acquired by all water quality monitoring stations in the water area range to be evaluated in a preset time period.
And step S420, calculating the total value of the water area to be evaluated for the water quality deterioration evaluation according to the acquired first abnormal data, second abnormal data and third abnormal data.
Specifically, the calculation formula of the total value of the water quality deterioration evaluation of the water area to be evaluated is as follows:
wherein,Yrepresenting the total value of the water quality abominability evaluation of the water area to be evaluated;
representing an accuracy factor for acquiring the first anomaly data;
an accuracy factor representing the acquisition of the second anomaly data;
an accuracy factor representing the acquisition of third anomaly data;
representing a total number of acquired first anomaly data;Qrepresenting the total number of acquired second abnormal data;Dindicating a total number of the acquired third exception data;
representing the total number of all water quality monitoring stations;iindicates to acquire the firstiA first anomaly data;jindicating the first in the first abnormal datajIndividual index data;Nrepresenting the total number of types of index data in the first abnormal data;
is shown asiFirst abnormal datajA severity factor for each index datum;
is shown asiFirst abnormal datajThe measured value of each index data;
is shown asiFirst abnormal datajStandard values of the individual index data;qis shown asqSecond anomaly data;eindicating the first in the second abnormal dataeIndividual index data;Erepresenting the total number of types of the index data in the second abnormal data;
is shown asqIn the second abnormal dataeA severity factor for each index datum;
is shown asqIn the second abnormal dataeThe measured value of each index data;
is shown asqIn the second abnormal dataeStandard values of the individual index data;
is shown asdA severity factor for the third anomaly data;
is shown asdAn actual value of the third anomaly data;
is shown asdStandard values of the third exception data;
the total number of index data overlapping each other in the first abnormality data, the second abnormality data, and the third abnormality data is represented.
The first abnormal data is full index data, the second abnormal data is related index data, and the third abnormal data is single index data.
And step S5, evaluating the water quality improvement condition of the water area to be evaluated according to the first abnormal data, the second abnormal data and the third abnormal data, and calculating the water quality improvement value of the water area to be evaluated.
Specifically, the calculation formula of the water quality improvement value of the water area to be evaluated is as follows:
wherein,
representing a water quality improvement value of a water area to be evaluated;
is shown as
Each moment;
representing the total time number of the collected water quality data;
representing an accuracy factor for acquiring the first anomaly data;
an accuracy factor representing the acquisition of the second anomaly data;
an accuracy factor representing the acquisition of third anomaly data;
representing a total number of acquired first anomaly data;Nrepresenting the total number of types of index data in the first abnormal data;Qrepresenting the total number of acquired second abnormal data;Erepresenting the total number of types of the index data in the second abnormal data;Dindicating a total number of the acquired third exception data;
is shown asiFirst abnormal datajThe weight of each index data;
is shown asqIn the second abnormal dataeThe weight of each index data;
is shown asdThe weight of the index data in the third exception data;
is shown as
The first moment of timeiFirst abnormal datajThe measured value of each index data;
is shown as
The first moment of timeiFirst abnormal datajThe measured value of each index data;
is shown as
The first moment of timeqIn the second abnormal dataeThe measured value of each index data;
indicating the acquisition of the first momentqIn the second abnormal dataeThe measured value of each index data;
is shown as
The first moment of timedAn actual value of the third anomaly data;
is shown as
The first moment of timedMeasured values of the third anomaly data.
Example two
As shown in fig. 5, the present application further provides a water quality index fusion data anomaly detection system 100, which includes:
the data acquisition device 10 is used for acquiring historical fusion data of water quality monitoring and monitoring data of the water quality automatic station at the current moment;
the model establishing module 20 is used for establishing a full-index isolated forest detection model, a correlation index abnormity detection model and a single-index abnormity detection model according to the acquired historical fusion data of water quality monitoring;
the abnormal data acquisition module 30 is used for inputting the acquired water quality automatic station monitoring data at the current moment into the established full-index isolated forest detection model, the established associated index abnormality detection model and the established single-index abnormality detection model, and respectively outputting first abnormal data, second abnormal data and third abnormal data;
and the data processor 40 is used for evaluating the water quality at the current moment according to the first abnormal data, the second abnormal data and the third abnormal data, and calculating the total evaluation value of the water quality badness of the water area to be evaluated.
And the data processor 40 is further configured to evaluate the water quality improvement condition of the water area to be evaluated according to the first abnormal data, the second abnormal data and the third abnormal data, and calculate a water quality improvement value of the water area to be evaluated.
The calculation formula of the total value of the water area to be evaluated for evaluating the water quality badness is as follows:
wherein,Yrepresenting the total value of the water quality abominability evaluation of the water area to be evaluated;
representing an accuracy factor for acquiring the first anomaly data;
an accuracy factor representing the acquisition of the second anomaly data;
an accuracy factor representing the acquisition of third anomaly data;
representing a total number of acquired first anomaly data;Qrepresenting the total number of acquired second abnormal data;Dindicating a total number of the acquired third exception data;
representing the total number of all water quality monitoring stations;iindicates to acquire the firstiA first anomaly data;jindicating the first in the first abnormal datajIndividual index data;Nrepresenting the total number of types of index data in the first abnormal data;
is shown asiFirst abnormal datajA severity factor for each index datum;
is shown asiFirst abnormal datajThe measured value of each index data;
is shown asiFirst abnormal datajStandard values of the individual index data;qis shown asqSecond anomaly data;eindicating the first in the second abnormal dataeIndividual index data;Erepresenting the total number of types of the index data in the second abnormal data;
is shown asqIn the second abnormal dataeA severity factor for each index datum;
is shown asqIn the second abnormal dataeThe measured value of each index data;
is shown asqIn the second abnormal dataeStandard values of the individual index data;
is shown asdA severity factor for the third anomaly data;
is shown asdAn actual value of the third anomaly data;
is shown asdStandard values of the third exception data;
the total number of index data overlapping each other in the first abnormality data, the second abnormality data, and the third abnormality data is represented.
Wherein, the calculation formula of the water quality improvement value of the water area to be evaluated is as follows:
wherein,
representing a water quality improvement value of a water area to be evaluated;
is shown as
Each moment;
representing the total time number of the collected water quality data;
representing an accuracy factor for acquiring the first anomaly data;
an accuracy factor representing the acquisition of the second anomaly data;
an accuracy factor representing the acquisition of third anomaly data;
representing a total number of acquired first anomaly data;Nrepresenting the total number of types of index data in the first abnormal data;Qrepresenting the total number of acquired second abnormal data;Eindicating the total type of index data in the second abnormal dataThe number of the particles;Dindicating a total number of the acquired third exception data;
is shown asiFirst abnormal datajThe weight of each index data;
is shown asqIn the second abnormal dataeThe weight of each index data;
is shown asdThe weight of the index data in the third exception data;
is shown as
The first moment of timeiFirst abnormal datajThe measured value of each index data;
is shown as
The first moment of timeiFirst abnormal datajThe measured value of each index data;
is shown as
The first moment of timeqIn the second abnormal dataeThe measured value of each index data;
is shown as
The first moment of timeqIn the second abnormal dataeThe measured value of each index data;
is shown as
The first moment of timedAn actual value of the third anomaly data;
is shown as
The first moment of timedMeasured values of the third anomaly data.
The first abnormal data is full index data, the second abnormal data is related index data, and the third abnormal data is single index data.
The beneficial effect that this application realized is as follows:
(1) according to the method, a set of multi-level abnormal value detection method aiming at multiple indexes, related indexes and single index is established, the abnormal value detection accuracy in the surface water environment monitoring data is effectively improved, the false detection rate and the missing detection rate of abnormal value detection are reduced, the authenticity and the objectivity of the monitoring data are guaranteed, and meanwhile, data support is provided for finding out that the water environment is about to deteriorate in advance.
(2) According to the method and the device, the water quality of the water area to be evaluated and the water quality improvement condition are evaluated according to the acquired first abnormal data, second abnormal data and third abnormal data, so that the water quality condition is comprehensively evaluated, whether the water quality condition of the current water quality to be evaluated meets the functional application of the water area to be evaluated is judged according to the functional application of the water area to be evaluated, whether the water quality improvement meets the requirement is judged according to the water quality improvement condition, and the water quality condition is better managed.
The above description is only an embodiment of the present invention, and is not intended to limit the present invention. Various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (10)
1. A water quality index fusion data abnormity detection method is characterized by comprising the following steps:
acquiring historical fusion data of water quality monitoring and monitoring data of a water quality automatic station at the current moment;
establishing a full-index isolated forest detection model, a correlation index abnormity detection model and a single-index abnormity detection model according to the acquired water quality monitoring history fusion data;
inputting the acquired monitoring data of the water quality automatic station at the current moment into the established full-index isolated forest detection model, the established associated index abnormality detection model and the established single-index abnormality detection model, and respectively outputting first abnormal data, second abnormal data and third abnormal data;
and evaluating the water quality at the current moment according to the first abnormal data, the second abnormal data and the third abnormal data, and calculating the total evaluation value of the water area to be evaluated for the water quality badness.
2. The method for detecting the abnormality of the water quality index fusion data according to claim 1, further comprising the steps of:
and evaluating the water quality improvement condition of the water area to be evaluated according to the first abnormal data, the second abnormal data and the third abnormal data, and calculating the water quality improvement value of the water area to be evaluated.
3. The water quality index fusion data abnormity detection method according to claim 1, wherein the method for establishing the full-index isolated forest detection model according to the acquired water quality monitoring history fusion data comprises the following steps:
selecting from historical fusion data of water quality monitoring
Taking the full index sample data as a subdata set, and putting the subdata set into a root node of an isolated tree;
wherein, height limit is set for the isolated tree;
randomly selecting an index data in the subdata set and randomly generating a cutting point
；
Less than cutting point in currently selected index data
Is placed in the left branch of the current node and is greater than or equal to the cut point
The point of (2) is placed at the right branch of the current node to form a new leaf node;
and continuously constructing new leaf nodes at the left branch node and the right branch node until only one index data is arranged on the leaf nodes, all the characteristics of the index data on the nodes are the same or the isolated tree grows to the set height limit.
4. The water quality index fusion data anomaly detection method according to claim 3, wherein the method for establishing the full-index isolated forest detection model further comprises the following steps:
and calculating the abnormal scores of all full index sample data in the solitary forest.
5. The method for detecting the abnormality of the water quality index fusion data according to claim 4, wherein the method for calculating the abnormality scores of all the full index sample data in the soliton forest comprises the following steps:
calculating the average path length of a single isolated tree;
calculating full index sample data according to the average path length of single isolated tree
The abnormality score of (1).
6. The method for detecting the abnormality of the water quality index fusion data according to claim 5, wherein the calculation formula of the abnormality score of the full index sample data is as follows:
wherein,
representing an abnormal score of the full index sample data;
sample data representing full index
Path length expectation in solitary forests;
sample data representing full index
The path length of (a); the path length is the number of edges that pass from the root node to the leaf nodes of the isolated tree.
7. The water quality index fusion data anomaly detection method according to claim 1, wherein the method for establishing the correlation index anomaly detection model according to the water quality monitoring historical fusion data comprises the following steps:
selecting a related index data set from the historical fusion data of water quality monitoring;
and establishing a correlation index abnormity detection model according to the correlation index data set.
8. The method for detecting the abnormality of the water quality index fusion data according to claim 7, wherein the step of establishing a correlation index abnormality detection model according to the correlation index data set comprises the substeps of:
calculating automatic station sample points
Distance to all other automation station sample points;
calculating automatic station sample points
To (1) a
Distance between two adjacent plates
；
Representing automatic station sample points
And an automated station sample site
The distance of (d);
obtaining all automated station sample points
To (1) a
Distance neighborhood
(ii) a First, the
Including sample points in the proximity of the robotic station
Is not more than the distance of
All of the automated station sample points of distance;
calculating automatic station sample points
The reachable distance of (a);
according to the automatic station sample point
Calculating the local reachable density of all the automatic station sample points;
and calculating the local outlier factor of the sample point of the automatic station according to the local reachable density.
9. The water quality index fusion data abnormity detection method according to claim 1, wherein a single index dynamic threshold model is established according to the water quality monitoring historical fusion data, and the method comprises the following steps:
selecting single index sample data from the historical fusion data of water quality monitoring;
defining index data time series of single index sample data as
The number of times is defined as
Establishing a linear regression model according to the index data time sequence;
and calculating the dynamic threshold interval of the index data at the next moment according to the linear regression model.
10. A water quality index fusion data anomaly detection system is characterized by comprising:
the data acquisition device is used for acquiring historical fusion data of water quality monitoring and monitoring data of the water quality automatic station at the current moment;
the model establishing module is used for establishing a full-index isolated forest detection model, a correlation index abnormity detection model and a single-index abnormity detection model according to the acquired historical fusion data of water quality monitoring;
the abnormal data acquisition module is used for inputting the acquired monitoring data of the water quality automatic station at the current moment into the established full-index isolated forest detection model, the established associated index abnormal detection model and the established single-index abnormal detection model, and respectively acquiring first abnormal data, second abnormal data and third abnormal data;
and the data processor is used for evaluating the water quality at the current moment according to the first abnormal data, the second abnormal data and the third abnormal data and calculating the total evaluation value of the water area to be evaluated for the water quality deterioration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110992212.2A CN113435547B (en) | 2021-08-27 | 2021-08-27 | Water quality index fusion data anomaly detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110992212.2A CN113435547B (en) | 2021-08-27 | 2021-08-27 | Water quality index fusion data anomaly detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113435547A true CN113435547A (en) | 2021-09-24 |
| CN113435547B CN113435547B (en) | 2021-11-16 |
Family
ID=77798190
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110992212.2A Active CN113435547B (en) | 2021-08-27 | 2021-08-27 | Water quality index fusion data anomaly detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113435547B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114022052A (en) * | 2022-01-04 | 2022-02-08 | 北京英视睿达科技股份有限公司 | Water quality abnormity monitoring method and device, storage medium and computer equipment |
| CN114039886A (en) * | 2021-10-19 | 2022-02-11 | 国网山东省电力公司日照供电公司 | Data correctness identification method and device based on four-differential and autocorrelation analysis |
| CN114527249A (en) * | 2022-01-17 | 2022-05-24 | 南方海洋科学与工程广东省实验室(广州) | Water quality monitoring data quality control method and system |
| CN114563463A (en) * | 2022-01-28 | 2022-05-31 | 上海普适导航科技股份有限公司 | Water quality data abnormity identification method and system |
| CN116011894A (en) * | 2023-03-28 | 2023-04-25 | 河北长发铝业股份有限公司 | Aluminum alloy rod production data management system |
| CN116933186A (en) * | 2023-09-14 | 2023-10-24 | 江苏新路德建设有限公司 | Sewage pipe network blocking real-time monitoring method based on data driving |
| CN117030964A (en) * | 2023-10-07 | 2023-11-10 | 哈尔滨凯纳科技股份有限公司 | Control system and method for water quality analyzer |
| CN117282261A (en) * | 2023-11-23 | 2023-12-26 | 天津恩纳社环保有限公司 | Microorganism waste gas treatment system |
| CN117874653A (en) * | 2024-03-11 | 2024-04-12 | 武汉佳华创新电气有限公司 | Power system safety monitoring method and system based on multi-source data |
| CN118094268A (en) * | 2024-03-01 | 2024-05-28 | 山东华奕生命科学有限公司 | Data processing method oriented to food safety supervision |
| CN118133211A (en) * | 2024-05-07 | 2024-06-04 | 山东世纪智慧农业科技有限公司 | Black termitomyces albuminosus stick pollution evaluation method based on multidimensional sensor |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504901A (en) * | 2014-12-29 | 2015-04-08 | 浙江银江研究院有限公司 | Multidimensional data based detecting method of traffic abnormal spots |
| CN110969556A (en) * | 2019-09-30 | 2020-04-07 | 上海仪电（集团）有限公司中央研究院 | Method and device for detecting river water quality abnormity by machine learning multi-dimension multi-model fusion |
| CN111507376A (en) * | 2020-03-20 | 2020-08-07 | 厦门大学 | Single index abnormality detection method based on fusion of multiple unsupervised methods |
| CN111553468A (en) * | 2020-05-15 | 2020-08-18 | 南京大学 | Method for accurately predicting effluent quality of sewage treatment plant |
| CN111740991A (en) * | 2020-06-19 | 2020-10-02 | 上海仪电（集团）有限公司中央研究院 | Anomaly detection method and system |
-
2021
- 2021-08-27 CN CN202110992212.2A patent/CN113435547B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504901A (en) * | 2014-12-29 | 2015-04-08 | 浙江银江研究院有限公司 | Multidimensional data based detecting method of traffic abnormal spots |
| CN110969556A (en) * | 2019-09-30 | 2020-04-07 | 上海仪电（集团）有限公司中央研究院 | Method and device for detecting river water quality abnormity by machine learning multi-dimension multi-model fusion |
| CN111507376A (en) * | 2020-03-20 | 2020-08-07 | 厦门大学 | Single index abnormality detection method based on fusion of multiple unsupervised methods |
| CN111553468A (en) * | 2020-05-15 | 2020-08-18 | 南京大学 | Method for accurately predicting effluent quality of sewage treatment plant |
| CN111740991A (en) * | 2020-06-19 | 2020-10-02 | 上海仪电（集团）有限公司中央研究院 | Anomaly detection method and system |
Non-Patent Citations (2)
| Title |
|---|
| 宋晓雅: "春节期间凉水河流域典型污水处理厂进水水质分析", 《给水排水增刊》 * |
| 赵云: "大连市重要江河湖泊水功能区达标评价研究", 《水资源开发与管理》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114039886A (en) * | 2021-10-19 | 2022-02-11 | 国网山东省电力公司日照供电公司 | Data correctness identification method and device based on four-differential and autocorrelation analysis |
| CN114022052A (en) * | 2022-01-04 | 2022-02-08 | 北京英视睿达科技股份有限公司 | Water quality abnormity monitoring method and device, storage medium and computer equipment |
| CN114527249A (en) * | 2022-01-17 | 2022-05-24 | 南方海洋科学与工程广东省实验室(广州) | Water quality monitoring data quality control method and system |
| CN114527249B (en) * | 2022-01-17 | 2024-03-19 | 南方海洋科学与工程广东省实验室(广州) | Quality control method and system for water quality monitoring data |
| CN114563463A (en) * | 2022-01-28 | 2022-05-31 | 上海普适导航科技股份有限公司 | Water quality data abnormity identification method and system |
| CN114563463B (en) * | 2022-01-28 | 2024-10-11 | 上海普适导航科技股份有限公司 | Water quality data anomaly identification method and system |
| CN116011894A (en) * | 2023-03-28 | 2023-04-25 | 河北长发铝业股份有限公司 | Aluminum alloy rod production data management system |
| CN116011894B (en) * | 2023-03-28 | 2023-06-02 | 河北长发铝业股份有限公司 | Aluminum alloy rod production data management system |
| CN116933186B (en) * | 2023-09-14 | 2023-11-24 | 江苏新路德建设有限公司 | Sewage pipe network blocking real-time monitoring method based on data driving |
| CN116933186A (en) * | 2023-09-14 | 2023-10-24 | 江苏新路德建设有限公司 | Sewage pipe network blocking real-time monitoring method based on data driving |
| CN117030964A (en) * | 2023-10-07 | 2023-11-10 | 哈尔滨凯纳科技股份有限公司 | Control system and method for water quality analyzer |
| CN117282261A (en) * | 2023-11-23 | 2023-12-26 | 天津恩纳社环保有限公司 | Microorganism waste gas treatment system |
| CN117282261B (en) * | 2023-11-23 | 2024-02-23 | 天津恩纳社环保有限公司 | Microorganism waste gas treatment system |
| CN118094268A (en) * | 2024-03-01 | 2024-05-28 | 山东华奕生命科学有限公司 | Data processing method oriented to food safety supervision |
| CN118094268B (en) * | 2024-03-01 | 2024-08-23 | 山东华奕生命科学有限公司 | Data processing method oriented to food safety supervision |
| CN117874653A (en) * | 2024-03-11 | 2024-04-12 | 武汉佳华创新电气有限公司 | Power system safety monitoring method and system based on multi-source data |
| CN117874653B (en) * | 2024-03-11 | 2024-05-31 | 武汉佳华创新电气有限公司 | Power system safety monitoring method and system based on multi-source data |
| CN118133211A (en) * | 2024-05-07 | 2024-06-04 | 山东世纪智慧农业科技有限公司 | Black termitomyces albuminosus stick pollution evaluation method based on multidimensional sensor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113435547B (en) | 2021-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113435547B (en) | Water quality index fusion data anomaly detection method and system | |
| Thornton et al. | Progress and prospects in mapping recent selection in the genome | |
| Nelson et al. | Genomewide analysis of admixture and adaptation in the Africanized honeybee | |
| Pool et al. | Inference of historical changes in migration rate from the lengths of migrant tracts | |
| Parejo et al. | Using whole-genome sequence information to foster conservation efforts for the European dark honey bee, Apis mellifera mellifera | |
| Berner et al. | Genomics of adaptive divergence with chromosome‐scale heterogeneity in crossover rate | |
| Daïnou et al. | Revealing hidden species diversity in closely related species using nuclear SNPs, SSRs and DNA sequences–a case study in the tree genus Milicia | |
| Hoti et al. | Bayesian mapping of genotype× expression interactions in quantitative and qualitative traits | |
| CN107402547A (en) | Unit exception detection method and system based on the point analysis that peels off | |
| CN116485020B (en) | Supply chain risk identification early warning method, system and medium based on big data | |
| CN112329944B (en) | Data flow concept drift detection method based on historical model diversity | |
| CN116308415A (en) | Sewage discharge data true and false risk assessment method | |
| Beer et al. | Genetic diversity, admixture, and hatchery influence in Brook Trout (Salvelinus fontinalis) throughout western New York State | |
| CN114038502B (en) | Method for associating expression quantitative trait with CNV based on gene interaction network clustering and group sparse learning | |
| Esnault et al. | Development of a potato cultivar (Solanum tuberosum L.) core collection, a valuable tool to prospect genetic variation for novel traits | |
| CN115858606A (en) | Method, device and equipment for detecting abnormity of time series data and storage medium | |
| Petkovski et al. | Anomaly detection on univariate sensing time series data for smart aquaculture using K-means, isolation forest, and local outlier factor | |
| CN116246705B (en) | Analysis method and device for whole genome sequencing data | |
| Aldridge et al. | Genetic and morphological patterns show variation in frequency of hybrids between Ipomopsis (Polemoniaceae) zones of sympatry | |
| Zimmerman et al. | A genetic warning system for a hierarchically structured wildlife monitoring framework | |
| CN117454295A (en) | Dynamic threshold abnormality detection method, system, storage medium and intelligent device | |
| CN110807174B (en) | Effluent analysis and abnormity identification method for sewage plant group based on statistical distribution | |
| CN110517731A (en) | Genetic test quality monitoring data processing method and system | |
| Piñeiro et al. | Contrasting dates of rainforest fragmentation in Africa inferred from trees with different dispersal abilities | |
| Tenaillon et al. | Apparent mutational hotspots and long distance linkage disequilibrium resulting from a bottleneck |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |