CN114254836A - Water bloom disaster early warning method and terminal based on similarity analysis - Google Patents
Water bloom disaster early warning method and terminal based on similarity analysis Download PDFInfo
- Publication number
- CN114254836A CN114254836A CN202111620749.2A CN202111620749A CN114254836A CN 114254836 A CN114254836 A CN 114254836A CN 202111620749 A CN202111620749 A CN 202111620749A CN 114254836 A CN114254836 A CN 114254836A
- Authority
- CN
- China
- Prior art keywords
- time
- similarity
- algae
- trend
- formula
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004458 analytical method Methods 0.000 title claims abstract description 27
- 241000192710 Microcystis aeruginosa Species 0.000 title abstract description 17
- 241000195493 Cryptophyta Species 0.000 claims abstract description 77
- 230000007613 environmental effect Effects 0.000 claims abstract description 53
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 47
- 238000012216 screening Methods 0.000 claims abstract description 22
- 238000005070 sampling Methods 0.000 claims description 36
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 8
- 208000035126 Facies Diseases 0.000 claims 1
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 239000005422 algal bloom Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000012952 Resampling Methods 0.000 description 1
- 230000001580 bacterial effect Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012851 eutrophication Methods 0.000 description 1
- 239000013505 freshwater Substances 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 206010037844 rash Diseases 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a water bloom disaster early warning method and a terminal based on similarity analysis, and the method comprises the following steps: step S1, algae data, meteorological data and water quality data are obtained, and the algae data, the meteorological data and the water quality data are preprocessed to form a standard time sequence with the same time frequency; step S2, calculating according to the algae data, the meteorological data and the water quality data of the standard time sequence to obtain the spatial distribution similarity; step S3, calculating according to the algae data, the meteorological data and the water quality data of the standard time sequence to obtain the similarity of environmental conditions; and S4, screening environmental condition similar time periods according to the environmental condition similarity, screening spatial distribution similar time points according to the spatial distribution similarity, and calculating to obtain the final follow-up trend grade according to the environmental condition similar time periods and the spatial distribution similar time points. The invention calculates the spatial similarity and the time similarity of the environment and obtains the subsequent trend grade of the algae condition.
Description
Technical Field
The invention relates to the technical field of disaster early warning, in particular to a water bloom disaster early warning method and a terminal based on similarity analysis.
Background
The water bloom refers to algae floating matters formed on the water surface and explosively propagated by certain algae due to eutrophication of water bodies in fresh water bodies, the water bloom not only damages water landscapes, but also stimulates bacterial breeding to seriously destroy the water bodies, inhibits the growth and propagation of beneficial planktons and harms cultivated animals, so that the physical and mental health of people is harmed, and as a multi-lake country in China, many lakes are affected by the water bloom disasters, for example, great blue algae eruptions occur in Taihu lakes, nested lakes and Dian ponds for many years continuously, Yanghu lakes, Dongting lakes, Er-Hai and other lakes are also subjected to water bloom disasters of different degrees, so that the country pays more and more attention to monitoring and early warning of the water disasters.
At present, the monitoring of the algal bloom disaster mainly depends on the laboratory analysis of algae water body samples collected by a laying station periodically and manually, or the blue algae algal bloom is inverted by constructing a water color remote sensing model. The early warning mainly comprises two methods, one is to establish a prediction model according to the combination of the concentration of algae cells and weather forecast, the other is to establish a water ecology dynamics model by considering the factors of nutrient substances, water flow, vertical water temperature distribution and the like, however, the former depends on the weather forecast precision seriously, and the latter has many factors influencing algae and is very complex in model establishment, so the current early warning technology of the water bloom disaster has certain limitation.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method and the terminal for early warning the water bloom disasters based on similarity analysis are provided for predicting the water bloom disasters.
In order to solve the technical problems, the invention adopts the technical scheme that:
a bloom disaster early warning method based on similarity analysis comprises the following steps:
step S1, algae data, meteorological data and water quality data are obtained, and the algae data, the meteorological data and the water quality data are preprocessed to form a standard time sequence with the same time frequency;
step S2, calculating to obtain spatial distribution similarity according to the algae data of the standard time sequence;
step S3, calculating according to the algae data, the meteorological data and the water quality data of the standard time sequence to obtain the similarity of environmental conditions;
and S4, screening environmental condition similar time periods according to the environmental condition similarity, screening spatial distribution similar time points according to the spatial distribution similarity, and calculating to obtain the final follow-up trend grade according to the environmental condition similar time periods and the spatial distribution similar time points.
In order to solve the technical problem, the invention adopts another technical scheme as follows:
a water bloom disaster early warning terminal based on similarity analysis comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the following steps:
step S1, algae data, meteorological data and water quality data are obtained, and the algae data, the meteorological data and the water quality data are preprocessed to form a standard time sequence with the same time frequency;
step S2, calculating to obtain spatial distribution similarity according to the algae data of the standard time sequence;
step S3, calculating according to the algae data, the meteorological data and the water quality data of the standard time sequence to obtain the similarity of environmental conditions;
and S4, screening environmental condition similar time periods according to the environmental condition similarity, screening spatial distribution similar time points according to the spatial distribution similarity, and calculating to obtain the final follow-up trend grade according to the environmental condition similar time periods and the spatial distribution similar time points.
The invention has the beneficial effects that: a bloom disaster early warning method and a terminal based on similarity analysis are disclosed, wherein the subsequent trend grade of algae conditions is obtained by calculating spatial distribution similarity and environmental condition similarity and according to the spatial distribution similarity and the environmental condition similarity, so that the bloom disaster is predicted.
Drawings
Fig. 1 is a flow diagram illustrating a bloom disaster warning method based on similarity analysis according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a bloom disaster warning terminal based on similarity analysis according to an embodiment of the present invention.
Description of reference numerals:
1. a bloom disaster early warning terminal based on similarity analysis; 2. a processor; 3. a memory.
Detailed Description
In order to explain technical contents, achieved objects, and effects of the present invention in detail, the following description is made with reference to the accompanying drawings in combination with the embodiments.
Referring to fig. 1, a method,
a bloom disaster early warning method based on similarity analysis comprises the following steps:
step S1, algae data, meteorological data and water quality data are obtained, and the algae data, the meteorological data and the water quality data are preprocessed to form a standard time sequence with the same time frequency;
step S2, calculating to obtain spatial distribution similarity according to the algae data of the standard time sequence;
step S3, calculating according to the algae data, the meteorological data and the water quality data of the standard time sequence to obtain the similarity of environmental conditions;
and S4, screening environmental condition similar time periods according to the environmental condition similarity, screening spatial distribution similar time points according to the spatial distribution similarity, and calculating to obtain the final follow-up trend grade according to the environmental condition similar time periods and the spatial distribution similar time points.
From the above description, the beneficial effects of the present invention are: the method has the advantages that the water bloom disasters are predicted by calculating the spatial distribution similarity and the environmental condition similarity and obtaining the subsequent trend grade of the algae conditions according to the spatial distribution similarity and the environmental condition similarity, and compared with the existing water bloom prediction method, the method is easy to realize and high in accuracy.
Further, the step S3 specifically includes:
step S31, calculating the correlation of all weather, water quality factors and algae changes by using the Pearson correlation coefficient;
step S32, taking the element with the absolute value of the correlation larger than the set value as the key element related to the algae change;
step S33, calculating the similarity of environmental conditions according to the key elements related to the algae change.
From the above description, it can be seen that the key elements to be calculated are obtained by screening the elements according to the correlation, and the environmental correlation is obtained by calculating the key elements, which reduces the complexity of calculation through screening, and makes the whole method easier to implement.
Further, the step S31 specifically includes:
for time series data, key elements related to algae change are screened by using a Pearson correlation coefficient, and the calculation formula is as follows:
where ρ represents correlation, A, B represents the time series of algae and the time series of individual meteorological or water quality elements, respectively, cov represents covariance, std represents standard deviation;
the step S33 specifically includes:
the environmental condition similarity is calculated according to the following formula:
in the formula, ωmThe element weight is obtained from the correlation of the elements, and d (x) is higher when the element weight is higher with higher correlationm,ym) Is the distance of a single element in two time series, Y is a plurality of element series of time a, and X is a plurality of element series of time b:
in the formula, m is a main element, so m in Y and X is equal, k and n are time lengths, and k is less than n;
distance d (x) of single element in two time seriesm,ym) Calculated according to the following formula:
in the formula IkIs xmAnd ymDistance of middle alignment point:
in the formula, i and j are index numbers in two sequences respectively, and lZDistance of the Z-th alignment point;
with the constraint:
{xmn',…,xmn”}∈xm,n”-n'=[k-2,k+2];
in the formula, n' is the initial position of interception, n "is the end position of interception, if:
lz-1=(xmn',ymk');
the next alignment point:
lz=(xmn,ymk);
the conditions are required to be satisfied: n-n 'is less than or equal to 1, k-k' is less than or equal to 1, n-n 'is more than or equal to 0, and k-k' is more than or equal to 0.
As can be seen from the above description, an example of a method for calculating the similarity of environmental conditions is given, which overcomes the disadvantage that euclidean distances have similarity that cannot distinguish between shapes and dynamic variation amplitudes through a dynamic time warping algorithm, and achieves minimum weighted distance sum through a local optimization method.
Further, the step S2 specifically includes:
the spatial similarity s _ spatial of time a and time b is calculated using the following equationa,b:
In the formula, s _ numa,bS _ trend, the numerical similarity of the spatial distribution of time a and time ba,bSimilarity of trends, ω, of the spatial distribution of time a and time bnumAnd ωtrendRespectively weighting the numerical similarity and the trend similarity;
wherein for numerical similarity s _ numa,bCalculated according to the following formula:
wherein x represents the algal cell concentration, i.e., xaiThe concentration of algal cells, x, at the time a sampling point ibiAlgal cell concentration, std, representing the sampling point i at time bxiIs the standard deviation, omega, of the algal cell concentration at all historical times for sample point iiThe weight representing sample point i is calculated using the following equation:
in the formula, ωiRepresenting the weight of the sample point i, N representing the total number of sample points, R representing the number of sub-regions to be divided, RiRepresenting sub-regions to which sample points i belongThe number of sampling points;
for trend similarity s _ trenda,bCalculated according to the following formula:
in the formula, raiThe ranking of the algal cell concentration at sample point i at time a in all samples, rbiThe ranking of algal cell concentration at sample point i at time b in all samples, stdriThe standard deviation of the algal cell concentration ranking for sampling point i over all historical times.
From the above description, it can be seen that a specific calculation method of spatial distribution similarity is provided, and calculation of spatial distribution similarity is achieved, wherein the lake region is divided into R sub-regions, and weight is allocated to each point location when numerical similarity is calculated, so that the similarity is prevented from being influenced too much by regions with dense sampling points.
Further, the step S4 specifically includes:
grading the subsequent trend of each similar time point or similar time period, calculating the change amplitude of the algae cell concentration of the similar time point or the similar time period and the next time point by taking the similar time point or the tail time point of the similar time period as a standard, obtaining a corresponding set score according to the grading of the subsequent trend, and calculating the score of the final trend grade according to the following formula:
in the formula, graderA grade representing the subsequent trend of similar time r, i represents the corresponding set score, simrIndicating the degree of similarity, trend, at a similar time riA score representing the final trend rating.
From the above description, the final trend grade score is obtained by performing weighted calculation on the trends of the similar time periods and time points, and the forecasting of the bloom disasters can be easily realized and calculated.
A water bloom disaster early warning terminal based on similarity analysis comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the following steps:
step S1, algae data, meteorological data and water quality data are obtained, and the algae data, the meteorological data and the water quality data are preprocessed to form a standard time sequence with the same time frequency;
step S2, calculating to obtain spatial distribution similarity according to the algae data of the standard time sequence;
step S3, calculating according to the algae data, the meteorological data and the water quality data of the standard time sequence to obtain the similarity of environmental conditions;
and S4, screening environmental condition similar time periods according to the environmental condition similarity, screening spatial distribution similar time points according to the spatial distribution similarity, and calculating to obtain the final follow-up trend grade according to the environmental condition similar time periods and the spatial distribution similar time points.
From the above description, the beneficial effects of the present invention are: the method has the advantages that the water bloom disasters are predicted by calculating the spatial distribution similarity and the environmental condition similarity and obtaining the subsequent trend grade of the algae conditions according to the spatial distribution similarity and the environmental condition similarity, and compared with the existing water bloom prediction method, the method is easy to realize and high in accuracy.
Further, the step S3 specifically includes:
step S31, calculating the correlation of all weather, water quality factors and algae changes by using the Pearson correlation coefficient;
step S32, taking the element with the absolute value of the correlation larger than the set value as the key element related to the algae change;
step S33, calculating the similarity of environmental conditions according to the key elements related to the algae change.
From the above description, it can be seen that the key elements to be calculated are obtained by screening the elements according to the correlation, and the environmental correlation is obtained by calculating the key elements, which reduces the complexity of calculation through screening, and makes the whole method easier to implement.
Further, the step S31 specifically includes:
for time series data, key elements related to algae change are screened by using a Pearson correlation coefficient, and the calculation formula is as follows:
where ρ represents correlation, A, B represents the time series of algae and the time series of individual meteorological or water quality elements, respectively, cov represents covariance, std represents standard deviation;
the step S33 specifically includes:
the environmental condition similarity is calculated according to the following formula:
in the formula, ωmThe element weight is obtained from the correlation of the elements, and d (x) is higher when the element weight is higher with higher correlationm,ym) Is the distance of a single element in two time series, Y is a plurality of element series of time a, and X is a plurality of element series of time b:
in the formula, m is a main element, so m in Y and X is equal, k and n are time lengths, and k is less than n;
distance d (x) of single element in two time seriesm,ym) Calculated according to the following formula:
in the formula IkIs xmAnd ymDistance of middle alignment point:
in the formula, i and j are index numbers in two sequences respectively, and lZDistance of the Z-th alignment point;
with the constraint:
{xmn',…,xmn”}∈xm,n”-n'=[k-2,k+2];
in the formula, n' is the initial position of interception, n "is the end position of interception, if:
lz-1=(xmn',ymk');
the next alignment point:
lz=(xmn,ymk);
the conditions are required to be satisfied: n-n 'is less than or equal to 1, k-k' is less than or equal to 1, n-n 'is more than or equal to 0, and k-k' is more than or equal to 0.
As can be seen from the above description, an example of a method for calculating the similarity of environmental conditions is given, which overcomes the disadvantage that euclidean distances have similarity that cannot distinguish between shapes and dynamic variation amplitudes through a dynamic time warping algorithm, and achieves minimum weighted distance sum through a local optimization method.
Further, the step S2 specifically includes:
the spatial similarity s _ spatial of time a and time b is calculated using the following equationa,b:
In the formula, s _ numa,bS _ trend, the numerical similarity of the spatial distribution of time a and time ba,bSimilarity of trends, ω, of the spatial distribution of time a and time bnumAnd ωtrendRespectively weighting the numerical similarity and the trend similarity;
wherein the content of the first and second substances,for numerical similarity s _ numa,bCalculated according to the following formula:
wherein x represents the algal cell concentration, i.e., xaiThe concentration of algal cells, x, at the time a sampling point ibiAlgal cell concentration, std, representing the sampling point i at time bxiIs the standard deviation, omega, of the algal cell concentration at all historical times for sample point iiThe weight representing sample point i is calculated using the following equation:
in the formula, ωiRepresenting the weight of the sample point i, N representing the total number of sample points, R representing the number of sub-regions to be divided, RiRepresenting the number of sampling points of a sub-region to which the sampling points i belong;
for trend similarity s _ trenda,bCalculated according to the following formula:
in the formula, raiThe ranking of the algal cell concentration at sample point i at time a in all samples, rbiThe ranking of algal cell concentration at sample point i at time b in all samples, stdriThe standard deviation of the algal cell concentration ranking for sampling point i over all historical times.
From the above description, it can be seen that a specific calculation method of spatial distribution similarity is provided, and calculation of spatial distribution similarity is achieved, wherein the lake region is divided into R sub-regions, and weight is allocated to each point location when numerical similarity is calculated, so that the similarity is prevented from being influenced too much by regions with dense sampling points.
Further, the step S4 specifically includes:
grading the subsequent trend of each similar time point or similar time period, calculating the change amplitude of the algae cell concentration of the similar time point or the similar time period and the next time point by taking the similar time point or the tail time point of the similar time period as a standard, obtaining a corresponding set score according to the grading of the subsequent trend, and calculating the score of the final trend grade according to the following formula:
in the formula, graderA grade representing the subsequent trend of similar time r, i represents the corresponding set score, simrIndicating the degree of similarity, trend, at a similar time riA score representing the final trend rating.
From the above description, the final trend grade score is obtained by performing weighted calculation on the trends of the similar time periods and time points, and the forecasting of the bloom disasters can be easily realized and calculated.
Referring to fig. 1, a first embodiment of the present invention is:
a bloom disaster early warning method based on similarity analysis comprises the following steps:
and step S1, acquiring algae data, meteorological data and water quality data, and preprocessing the algae data, the meteorological data and the water quality data to form a standard time sequence with the same time frequency.
Specifically, the algae data, the meteorological data and the water quality data are preprocessed by a standard time sequence including outlier rejection, null filling and resampling to the same time frequency.
And step S2, calculating the spatial distribution similarity according to the standard time series algae data.
Calculating the space distribution similarity s _ spatial of the time a and the time b according to the algae cell concentration numerical similarity of each point and the trend similarity of the algae cells of each pointa,b;
Wherein, the time a refers to the current sampling time point, and the time b refers to the historical sampling time points.
Specifically, the spatial similarity s _ spatial is calculated by the following equationa,b:
In the formula, s _ numa,bS _ trend, the numerical similarity of the spatial distribution of time a and time ba,bSimilarity of trends, ω, of the spatial distribution of time a and time bnumAnd ωtrendThe weights are respectively numerical similarity and trend similarity, and are given by technical personnel according to actual conditions, in the embodiment, the weight omega of the numerical similarity isnumSpecifically 0.7, weight ω of trend similaritytrendSpecifically 0.3.
Wherein for numerical similarity s _ numa,bCalculated according to the following formula:
wherein x represents the algal cell concentration, i.e., xaiThe concentration of algal cells, x, at the time a sampling point ibiAlgal cell concentration, std, representing the sampling point i at time bxiIs the standard deviation, omega, of the algal cell concentration at all historical times for sample point iiRepresenting the weight of sample point i.
The lake area is divided into R sub-areas in order to avoid that the similarity is greatly influenced by the dense areas of the sampling points, the weight is distributed to each point location when the numerical similarity is calculated, and the weight calculation formula of each point location is as follows:
in the formula, ωiRepresents the weight of the sample point i, N represents the total number of sample points, and R representsDividing the number of sub-regions, RiRepresenting the number of sampling points of the sub-region to which the sampling point i belongs.
While for the trend similarity s _ trenda,bCalculated according to the following formula:
in the formula, raiThe ranking of the algal cell concentration at sample point i at time a in all samples, rbiThe ranking of algal cell concentration at sample point i at time b in all samples, stdriThe standard deviation of the algal cell concentration ranking for sampling point i over all historical times.
And step S3, calculating the similarity of the environmental conditions according to the algae data, the meteorological data and the water quality data of the standard time series.
Specifically, step S3 includes:
step S31, calculating the correlation of all weather, water quality factors and algae changes by using the Pearson correlation coefficient;
specifically, regarding the similarity of environmental conditions, the key elements related to algae changes are screened by using the pearson correlation coefficient for time series data, and the calculation formula is as follows:
where ρ represents correlation, A, B represents the time series of algae and individual meteorological or water quality elements, respectively, cov represents covariance, std represents standard deviation.
Step S32, an element with the absolute value of correlation larger than 0.5 is taken as a key element related to the algae change.
Step S33, calculating the similarity of environmental conditions according to the key elements related to the algae change.
Specifically, when a plurality of main element sequences at time a is denoted by Y and a plurality of main element sequences at time b is denoted by X, there are:
in the formula, m is a main element, so m is equal to m in Y and X, k and n are time lengths, and k is less than n.
Then the historical time set R with similar weather and water quality conditions is:
R={Xi|Find(Sim(Xi,Y)),Xi∈X};
it can be seen that Y and X are both multivariate time series due to the presence of multiple influencing elements, and the univariate-based time series similarity measure is improved when searching for similar times. Common univariate-based Time sequence similarity measurement methods include Euclidean distance, Dynamic Time Warping (DTW) and the like, wherein the DTW algorithm overcomes the defect that the Euclidean distance has similarity of indistinguishable shape and Dynamic change amplitude, and the minimum sum of weighted distances is realized by a local optimization method, so that the similarity of Time sequences is calculated by adopting an improved DTW algorithm.
Specifically, for two time series in which m influencing elements exist, the similarity of environmental conditions is calculated as:
in the formula, ωmThe element weight is obtained from the correlation of the elements, and d (x) is higher when the element weight is higher with higher correlationm,ym) Solving the distance of a single element in two time sequences by adopting a DTW (delay tolerant shift) method, and setting xmAnd ymDistance of middle alignment point:
in the formula, i and j are index numbers in two sequences respectively, then:
since the path must start from the start point and end at the end point, i.e. the head and tail of the two sequences must match, it has boundary conditions:
l1=(xmn',ym1),lz=(xmn”,ymk);
wherein:
{xmn',…,xmn”}∈xm,n”-n'=[k-2,k+2];
in the formula, n 'is the initial position of interception, n' is the end position of interception, and n '-n' limits that the time length of interception and the target sequence can not differ by more than two time units.
Since it is not possible to align across a point, each point of the two sequences needs to be matched, which has continuity if:
lz-1=(xmn',ymk');
the next alignment point
lz=(xmn,ymk);
The conditions are required to be satisfied: n-n 'is less than or equal to 1, and k-k' is less than or equal to 1;
because the alignment point is monotonously performed along with the time, the two alignment lines are ensured not to be intersected and also have monotonicity, if:
lz-1=(xmn',ymk');
the next alignment point
lz=(xmn,ymk);
The conditions are required to be satisfied: n-n 'is not less than 0 and k-k' is not less than 0.
And S4, screening environmental condition similar time periods according to the environmental condition similarity, screening spatial distribution similar time points according to the spatial distribution similarity, and calculating to obtain the final follow-up trend grade according to the environmental condition similar time periods and the spatial distribution similar time points.
Specifically, each subsequent trend is graded, including five grades of large-amplitude rising, slight rising, gradual trend, slight falling and large-amplitude falling, the variation amplitude of the algae cell concentration between the subsequent trend and the next time point is calculated by taking the similar time point or the end time point of the similar time period as a standard, the final trend is graded by taking 0.4, 0.1, -0.1 and-0.4 as boundary values, and then the final trend grade is obtained by weighted average:
in the formula, graderShowing the subsequent trend of variation, sim, of similar time rrIndicating the degree of similarity, trend, at a similar time riA score representing the final trend rating.
Referring to fig. 2, the second embodiment of the present invention is:
a similarity analysis-based bloom disaster early warning method terminal 1 comprises a memory 3, a processor 2 and a computer program which is stored on the memory 3 and can run on the processor 2, wherein the first step of the embodiment is realized when the processor 2 executes the computer program.
In summary, the similarity analysis-based bloom disaster early warning method and the terminal provided by the invention predict the bloom disasters by calculating the space similarity and the time similarity of the environment, obtaining the subsequent trend grade of the algae condition according to the time similarity and the space similarity of the environment, and comparing with the existing bloom prediction method, the method has the advantages of easy realization and high accuracy, screening the elements according to the correlation to obtain the key elements needing to be calculated, calculating the key elements to obtain the environment correlation, reducing the complexity of calculation through screening to make the whole method easier to realize, overcoming the defect that the Euclidean distance has similarity with indistinguishable shape and dynamic change amplitude through a dynamic time warping algorithm, realizing the minimum sum of weighted distances through a local optimization method, by dividing the lake region into R sub-regions, weight is distributed to each point location when numerical similarity is calculated, and the phenomenon that the similarity is influenced too much by the region with dense sampling points is avoided.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent changes made by using the contents of the present specification and the drawings, or applied directly or indirectly to the related technical fields are included in the scope of the present invention.
Claims (10)
1. A bloom disaster early warning method based on similarity analysis is characterized by comprising the following steps:
step S1, algae data, meteorological data and water quality data are obtained, and the algae data, the meteorological data and the water quality data are preprocessed to form a standard time sequence with the same time frequency;
step S2, calculating to obtain spatial distribution similarity according to the algae data of the standard time sequence;
step S3, calculating according to the algae data, the meteorological data and the water quality data of the standard time sequence to obtain the similarity of environmental conditions;
and S4, screening environmental condition similar time periods according to the environmental condition similarity, screening spatial distribution similar time points according to the spatial distribution similarity, and calculating to obtain the final follow-up trend grade according to the environmental condition similar time periods and the spatial distribution similar time points.
2. The bloom disaster warning method based on similarity analysis as claimed in claim 1, wherein the step S3 specifically comprises:
step S31, calculating the correlation of all weather, water quality factors and algae changes by using the Pearson correlation coefficient;
step S32, taking the element with the absolute value of the correlation larger than the set value as the key element related to the algae change;
step S33, calculating the similarity of environmental conditions according to the key elements related to the algae change.
3. The bloom disaster warning method based on similarity analysis as claimed in claim 2, wherein the step S31 specifically comprises:
for time series data, key elements related to algae change are screened by using a Pearson correlation coefficient, and the calculation formula is as follows:
where ρ represents correlation, A, B represents the time series of algae and the time series of individual weather or water quality elements, respectively, cov represents covariance, std represents standard deviation;
the step S33 specifically includes:
the environmental condition similarity is calculated according to the following formula:
in the formula, ωmThe element weight is obtained from the correlation of elements, and d (x) is higher when the element weight is higher with higher correlationm,ym) Is the distance of a single element in two time series, Y is a plurality of element series of time a, and X is a plurality of element series of time b:
in the formula, m is a main element, so m in Y and X is equal, k and n are time lengths, and k is less than n;
distance d (x) of single element in two time seriesm,ym) Calculated according to the following formula:
in the formula IkIs xmAnd ymDistance of middle alignment point:
in the formula, i and j are index numbers in two sequences respectively, and lZDistance of the Z-th alignment point;
with the constraint:
{xmn',…,xmn”}∈xm,n”-n'=[k-2,k+2];
in the formula, n' is the initial position of interception, n "is the end position of interception, if:
lz-1=(xmn',ymk');
the next alignment point:
lz=(xmn,ymk);
the conditions are required to be satisfied: n-n 'is less than or equal to 1, k-k' is less than or equal to 1, n-n 'is more than or equal to 0, and k-k' is more than or equal to 0.
4. The bloom disaster warning method based on similarity analysis as claimed in claim 1, wherein the step S2 specifically comprises:
the spatial similarity s _ spatial of time a and time b is calculated using the following equationa,b:
In the formula, s _ numa,bS _ trend, the numerical similarity of the spatial distribution of time a and time ba,bSimilarity of trends, ω, of the spatial distribution of time a and time bnumAnd ωtrendWeights of numerical similarity and trend similarity respectively;
wherein for numerical similarity s _ numa,bCalculated according to the following formula:
wherein x represents the algal cell concentration, i.e., xaiThe concentration of algal cells, x, at the time a sampling point ibiAlgal cell concentration, std, representing the sampling point i at time bxiIs the standard deviation, omega, of the algal cell concentration at all the historical times for the sampling point iiThe weight representing sample point i is calculated using the following equation:
in the formula, ωiRepresenting the weight of the sampling point i, N representing the total number of sampling points, R representing the number of sub-regions to be divided, RiRepresenting the number of sampling points of a sub-region to which the sampling points i belong;
for trend similarity s _ trenda,bCalculated according to the following formula:
in the formula, raiThe ranking of the algal cell concentration at sample point i at time a in all samples, rbiThe ranking of algal cell concentration at sample point i at time b in all samples, stdriThe standard deviation of the algal cell concentration ranking for sampling point i over all historical times.
5. The bloom disaster warning method based on similarity analysis as claimed in claim 1, wherein the step S4 specifically comprises:
grading each similar time point or the subsequent trend of the similar time period, calculating the change range of the algae cell concentration between the similar time point or the tail time point of the similar time period and the next time point by taking the similar time point or the tail time point of the similar time period as a standard, obtaining a corresponding set score according to the grading of the subsequent trend, and calculating the score of the final trend grade according to the following formula:
in the formula, graderA grade representing the subsequent trend of similar time r, i represents the corresponding set score, simrIndicating the degree of similarity, trend, at a similar time riA score representing the final trend rating.
6. A bloom disaster early warning terminal based on similarity analysis comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, and is characterized in that the processor executes the computer program to realize the following steps:
step S1, algae data, meteorological data and water quality data are obtained, and the algae data, the meteorological data and the water quality data are preprocessed to form a standard time sequence with the same time frequency;
step S2, calculating to obtain spatial distribution similarity according to the algae data of the standard time sequence;
step S3, calculating according to the algae data, the meteorological data and the water quality data of the standard time sequence to obtain the similarity of environmental conditions;
and S4, screening environmental condition similar time periods according to the environmental condition similarity, screening spatial distribution similar time points according to the spatial distribution similarity, and calculating to obtain the final follow-up trend grade according to the environmental condition similar time periods and the spatial distribution similar time points.
7. The bloom disaster warning terminal based on similarity analysis as claimed in claim 6, wherein the step S3 specifically comprises:
step S31, calculating the correlation of all weather, water quality factors and algae changes by using the Pearson correlation coefficient;
step S32, taking the element with the absolute value of the correlation larger than the set value as the key element related to the algae change;
step S33, calculating the similarity of environmental conditions according to the key elements related to the algae change.
8. The bloom disaster warning terminal based on similarity analysis as claimed in claim 7, wherein the step S31 specifically comprises:
for time series data, key elements related to algae change are screened by using a Pearson correlation coefficient, and the calculation formula is as follows:
where ρ represents correlation, A, B represents the time series of algae and the time series of individual weather or water quality elements, respectively, cov represents covariance, std represents standard deviation;
the step S33 specifically includes:
the environmental condition similarity is calculated according to the following formula:
in the formula, ωmThe element weight is obtained from the correlation of elements, and d (x) is higher when the element weight is higher with higher correlationm,ym) Is the distance of a single element in two time series, Y is a plurality of element series of time a, and X is a plurality of element series of time b:
in the formula, m is a main element, so m in Y and X is equal, k and n are time lengths, and k is less than n;
distance d (x) of single element in two time seriesm,ym) Calculated according to the following formula:
in the formula IkIs xmAnd ymDistance of middle alignment point:
in the formula, i and j are index numbers in two sequences respectively, and lZDistance of the Z-th alignment point;
with the constraint:
{xmn',…,xmn”}∈xm,n”-n'=[k-2,k+2];
in the formula, n' is the initial position of interception, n "is the end position of interception, if:
lz-1=(xmn',ymk');
the next alignment point:
lz=(xmn,ymk);
the conditions are required to be satisfied: n-n 'is less than or equal to 1, k-k' is less than or equal to 1, n-n 'is more than or equal to 0, and k-k' is more than or equal to 0.
9. The bloom disaster warning terminal based on similarity analysis as claimed in claim 6, wherein the step S2 specifically comprises:
the spatial similarity s _ spatial of time a and time b is calculated using the following equationa,b:
In the formula, s _ numa,bS _ trend, the numerical similarity of the spatial distribution of time a and time ba,bSimilarity of trends, ω, of the spatial distribution of time a and time bnumAnd ωtrendNumerical similarity and trend facies, respectivelyA weight of the similarity;
wherein for numerical similarity s _ numa,bCalculated according to the following formula:
wherein x represents the algal cell concentration, i.e., xaiThe concentration of algal cells, x, at the time a sampling point ibiAlgal cell concentration, std, representing the sampling point i at time bxiIs the standard deviation, omega, of the algal cell concentration at all the historical times for the sampling point iiThe weight representing sample point i is calculated using the following equation:
in the formula, ωiRepresenting the weight of the sampling point i, N representing the total number of sampling points, R representing the number of sub-regions to be divided, RiRepresenting the number of sampling points of a sub-region to which the sampling points i belong;
for trend similarity s _ trenda,bCalculated according to the following formula:
in the formula, raiThe ranking of the algal cell concentration at sample point i at time a in all samples, rbiThe ranking of algal cell concentration at sample point i at time b in all samples, stdriThe standard deviation of the algal cell concentration ranking for sampling point i over all historical times.
10. The bloom disaster warning terminal based on similarity analysis as claimed in claim 6, wherein the step S4 specifically comprises:
grading each similar time point or the subsequent trend of the similar time period, calculating the change range of the algae cell concentration between the similar time point or the tail time point of the similar time period and the next time point by taking the similar time point or the tail time point of the similar time period as a standard, obtaining a corresponding set score according to the grading of the subsequent trend, and calculating the score of the final trend grade according to the following formula:
in the formula, graderA grade representing the subsequent trend of similar time r, i represents the corresponding set score, simrIndicating the degree of similarity, trend, at a similar time riA score representing the final trend rating.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111620749.2A CN114254836A (en) | 2021-12-28 | 2021-12-28 | Water bloom disaster early warning method and terminal based on similarity analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111620749.2A CN114254836A (en) | 2021-12-28 | 2021-12-28 | Water bloom disaster early warning method and terminal based on similarity analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114254836A true CN114254836A (en) | 2022-03-29 |
Family
ID=80795360
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111620749.2A Pending CN114254836A (en) | 2021-12-28 | 2021-12-28 | Water bloom disaster early warning method and terminal based on similarity analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114254836A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115240060A (en) * | 2022-09-22 | 2022-10-25 | 海南浙江大学研究院 | Starfish disaster early warning method and system |
-
2021
- 2021-12-28 CN CN202111620749.2A patent/CN114254836A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115240060A (en) * | 2022-09-22 | 2022-10-25 | 海南浙江大学研究院 | Starfish disaster early warning method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Camera et al. | A high resolution map of soil types and physical properties for Cyprus: A digital soil mapping optimization | |
Zeraatpisheh et al. | Conventional and digital soil mapping in Iran: Past, present, and future | |
Zou et al. | Artificial neural network and time series models for predicting soil salt and water content | |
Matsumura et al. | Maize yield forecasting by linear regression and artificial neural networks in Jilin, China | |
Emilio et al. | Soil physical conditions limit palm and tree basal area in Amazonian forests | |
Robbins et al. | Regional variation in successional trajectories and rates of vegetation change on glacier forelands in south-central Norway | |
CN103529189B (en) | A kind of soil organism space distribution Forecasting Methodology based on quantitative and qualitative analysis auxiliary variable | |
Chi et al. | Mapping soil total nitrogen in an estuarine area with high landscape fragmentation using a multiple-scale approach | |
CN104020274A (en) | Method for remote sensing quantitative estimation on woodland site quality | |
CN113011372B (en) | Automatic monitoring and identifying method for saline-alkali soil | |
CN114254836A (en) | Water bloom disaster early warning method and terminal based on similarity analysis | |
Izdebski et al. | On the use of palynological data in economic history: new methods and an application to agricultural output in Central Europe, 0–2000 AD | |
Chen et al. | Improving the practicability of remote sensing data-assimilation-based crop yield estimations over a large area using a spatial assimilation algorithm and ensemble assimilation strategies | |
CN108205718B (en) | Grain crop sampling yield measurement method and system | |
CN105528523A (en) | Soil thickness inversion method based on remote sensing data | |
Pham et al. | Head-cut gully erosion susceptibility modelling based on ensemble Random Forest with oblique decision trees in Fareghan watershed, Iran | |
CN115660166A (en) | Method and device for estimating yield of multiple crops, electronic equipment and storage medium | |
Yao et al. | Determining soil salinity and plant biomass response for a farmed coastal cropland using the electromagnetic induction method | |
CN104834966A (en) | Fishery forecasting method based on ant colony classifying algorithm | |
CN110363675A (en) | A kind of wheat scab monitoring method based on satellite remote sensing | |
Wang et al. | The phenotypic diversity of Schisandra sphenanthera fruit and SVR model for phenotype forecasting | |
CN108154263B (en) | Monitoring and predicting method for natural water resource | |
Hatfield | Spatial statistics | |
Crabbe et al. | Computer modelling and estimation of recruitment patterns of non-branching coral colonies at three sites in the Wakatobi Marine Park, SE Sulawesi, Indonesia; implications for coral reef conservation | |
CN114493182A (en) | Ecological health evaluation method and device for urban river channels in plain river network area |
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 |