CN118332444A - Urban lake nutrition level prediction method based on climate and socioeconomic index - Google Patents
Urban lake nutrition level prediction method based on climate and socioeconomic index Download PDFInfo
- Publication number
- CN118332444A CN118332444A CN202410763534.3A CN202410763534A CN118332444A CN 118332444 A CN118332444 A CN 118332444A CN 202410763534 A CN202410763534 A CN 202410763534A CN 118332444 A CN118332444 A CN 118332444A
- Authority
- CN
- China
- Prior art keywords
- index
- socioeconomic
- climate
- prediction
- nutrition
- 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
- 235000016709 nutrition Nutrition 0.000 title claims abstract description 99
- 230000035764 nutrition Effects 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 39
- 238000007637 random forest analysis Methods 0.000 claims abstract description 25
- 238000004422 calculation algorithm Methods 0.000 claims description 33
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 32
- 238000004458 analytical method Methods 0.000 claims description 30
- 238000012216 screening Methods 0.000 claims description 13
- 238000004457 water analysis Methods 0.000 claims description 13
- 235000003715 nutritional status Nutrition 0.000 claims description 10
- 241000195493 Cryptophyta Species 0.000 claims description 8
- 239000002028 Biomass Substances 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000007774 longterm Effects 0.000 claims 1
- 238000011161 development Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000002310 reflectometry Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000012851 eutrophication Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000001747 exhibiting effect Effects 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000003809 water extraction Methods 0.000 description 1
Classifications
-
- 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
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of environment prediction, and particularly discloses a method for predicting urban lake nutrition level based on climate and socioeconomic indexes, which comprises the following steps: acquiring satellite images aiming at urban lake areas; determining a long-time-sequence nutritional state index of the urban lake area based on the satellite image; determining a climate index and a socioeconomic index affecting the urban lake area; training a random forest model based on the long-time-sequence nutrition state index, the climate index and the socioeconomic index to generate a prediction model; and executing urban lake nutrition state index prediction based on the prediction model to generate a prediction result. The existing lake nutrition prediction method is improved, so that the prediction difficulty is reduced, and the prediction efficiency and the prediction precision are improved.
Description
Technical Field
The invention relates to the technical field of environment prediction, in particular to a method for predicting urban lake nutrition level based on climate and socioeconomic indexes.
Background
The urban lake is taken as an important component of the urban ecological environment, and has key effects on regulating climate, maintaining biodiversity, providing water resources and the like.
Eutrophication problems are driven by both climate conditions and socioeconomic development. In terms of climate conditions, climate factors such as water temperature, precipitation amount, sunshine time and the like directly influence the dissolved oxygen condition in the water body, and further indirectly influence the growth and propagation speed of aquatic organisms.
In the future, climate change and socioeconomic development will still have a serious impact on the eutrophication problem of urban lakes. Existing prediction techniques are typically based on complex physical models, which require large amounts of measured data at high acquisition costs to run, and consume large amounts of computational resources and time. The prediction efficiency is low and the prediction cost is high.
Disclosure of Invention
In order to overcome the technical problems in the prior art, the embodiment of the invention provides a city lake nutrition level prediction method based on weather and social economic indexes, and the prediction difficulty is reduced and the prediction efficiency and the prediction precision are improved by improving the existing lake nutrition prediction method.
In order to achieve the above object, an embodiment of the present invention provides a method for predicting nutrition levels of urban lakes based on climate and socioeconomic indexes, the method comprising: acquiring satellite images aiming at urban lake areas; determining a long-time-sequence nutritional state index of the urban lake area based on the satellite image; determining a climate index and a socioeconomic index affecting the urban lake area; training a random forest model based on the long-time-sequence nutrition state index, the climate index and the socioeconomic index to generate a prediction model; and executing urban lake nutrition state index prediction based on the prediction model to generate a prediction result.
Preferably, the determining the long time-series nutritional status index of the city lake region based on the satellite image includes: preprocessing the satellite image to obtain a preprocessed image; carrying out water analysis on the preprocessed image to generate a water analysis result; performing inversion operation of a long-time-sequence nutrition state index for the urban lake area based on the preprocessed image and the water body analysis result to obtain an inversion result; and generating a long-time-sequence nutrition state index of the urban lake area based on the inversion result.
Preferably, the performing an inversion operation for the long-time-series nutrition state index of the city lake region based on the preprocessed image and the water body analysis result, to obtain an inversion result, includes: performing nutrition state decomposition analysis on the water body analysis result based on a turbid water body extraction algorithm to obtain a first nutrition state area and a second nutrition state area; performing nutrition index analysis on the first nutrition status area based on a first preset algorithm to generate a first intermediate index, wherein the first preset algorithm is characterized in that: ; and carrying out nutrition index analysis on the second nutrition status area based on a second preset algorithm to generate a second intermediate index, wherein the second preset algorithm is characterized in that: ; wherein ABI OLI is characterized as an algae biomass index ABI calculated from OLI data in the pre-processed image, the algae biomass index ABI is characterized as: wherein R BLUE、RRED and R NIR are characterized as surface reflectance data for TM and etm+ spectra in the pre-processed image having wavelengths of 485 nm, 660nm and 835nm, respectively, and R BLUE、RRED and R NIR are surface reflectance data for OLI images having wavelengths of 482nm, 655nm and 865nm, respectively, and λ BLUE、λGREEN、λRED、λNIR is characterized as the center wavelength of each satellite's corresponding band; and performing lake inversion operation based on the first intermediate index and the second intermediate index to obtain an inversion result.
Preferably, said determining climate and socioeconomic metrics affecting said urban lake area comprises: determining an initial climate index based on the lunar meteorological data of the city lake region; acquiring agricultural parameters, population parameters and economic parameters corresponding to the urban lake area, and generating initial socioeconomic indexes based on the agricultural parameters, the population parameters and the economic parameters; analyzing the initial climate index and the initial socioeconomic index based on a pearson correlation algorithm to generate a key climate index and a key socioeconomic index; and screening the key climate indexes and the key socioeconomic indexes according to a preset screening rule to generate climate indexes and socioeconomic indexes of the urban lake area.
Preferably, the training the random forest model based on the long time-series nutrition state index, the climate index and the socioeconomic index to generate a prediction model includes: training the random forest model based on the long-time-sequence nutrition state index, the climate index and the socioeconomic index to obtain a preliminary training model; based on a preset parameter adjustment algorithm, carrying out parameter combination analysis on parameters of the preliminary training model, and outputting an optimal parameter combination; and adjusting the random forest model based on the optimal parameter combination to generate a prediction model.
Preferably, the predicting the nutritional state index of the city lake based on the prediction model is performed, and the generating a prediction result includes: determining preset scene conditions; executing urban lake nutrition state index prediction based on the preset scenario conditions and the prediction model to generate an initial result; and classifying the nutritional state of the initial result based on the nutritional state classification standard to obtain a predicted result.
Correspondingly, the invention also provides a city lake nutrition level prediction device based on climate and socioeconomic indexes, which comprises: the image acquisition unit is used for acquiring satellite images aiming at urban lake areas; the index generation unit is used for determining a long-time-sequence nutrition state index of the urban lake area based on the satellite images; an index determining unit for determining a climate index and a socioeconomic index affecting the urban lake area; the model training unit is used for training a random forest model based on the long-time sequence nutrition state index, the climate index and the socioeconomic index to generate a prediction model; and the prediction unit is used for performing urban lake nutrition state index prediction based on the prediction model and generating a prediction result.
Preferably, the index generating unit is specifically configured to: preprocessing the satellite image to obtain a preprocessed image; carrying out water analysis on the preprocessed image to generate a water analysis result; performing inversion operation of a long-time-sequence nutrition state index for the urban lake area based on the preprocessed image and the water body analysis result to obtain an inversion result; and generating a long-time-sequence nutrition state index of the urban lake area based on the inversion result.
Preferably, the index determining unit is specifically configured to: determining an initial climate index based on the lunar meteorological data of the city lake region; acquiring agricultural parameters, population parameters and economic parameters corresponding to the urban lake area, and generating initial socioeconomic indexes based on the agricultural parameters, the population parameters and the economic parameters; analyzing the initial climate index and the initial socioeconomic index based on a pearson correlation algorithm to generate a key climate index and a key socioeconomic index; and screening the key climate indexes and the key socioeconomic indexes according to a preset screening rule to generate climate indexes and socioeconomic indexes of the urban lake area.
Preferably, the model training unit is specifically configured to: training the random forest model based on the long-time-sequence nutrition state index, the climate index and the socioeconomic index to obtain a preliminary training model; based on a preset parameter adjustment algorithm, carrying out parameter combination analysis on parameters of the preliminary training model, and outputting an optimal parameter combination; and adjusting the random forest model based on the optimal parameter combination to generate a prediction model.
Through the technical scheme provided by the invention, the invention has at least the following technical effects:
The existing lake nutrition prediction method is improved, the intelligent model is trained based on satellite image data, so that a prediction model with higher prediction accuracy and lower operation difficulty is generated, the prediction difficulty can be greatly reduced in the prediction process, the prediction accuracy is effectively improved, and the actual requirements are met.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain, without limitation, the embodiments of the invention. In the drawings:
FIG. 1 is a flowchart of a specific implementation of a method for predicting urban lake nutrition level based on climate and socioeconomic index according to an embodiment of the present invention;
FIG. 2 is a flowchart of a specific implementation of determining a long-time nutritional status index provided by an embodiment of the present invention;
FIG. 3 is a flowchart of a specific implementation of determining climate indicators and socioeconomic indicators provided by an embodiment of the present invention;
FIG. 4 is a schematic diagram of a predicted result of a lake nutritional status index under a set scenario according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an urban lake nutrition level prediction device based on climate and socioeconomic indexes according to an embodiment of the present invention.
Detailed Description
The following describes the detailed implementation of the embodiments of the present invention with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
The terms "system" and "network" in embodiments of the invention may be used interchangeably. "plurality" means two or more, and "plurality" may also be understood as "at least two" in this embodiment of the present invention. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/", unless otherwise specified, generally indicates that the associated object is an "or" relationship. In addition, it should be understood that in the description of embodiments of the present invention, the words "first," "second," and the like are used merely for distinguishing between the descriptions and not be construed as indicating or implying a relative importance or order.
Referring to fig. 1, an embodiment of the present invention provides a method for predicting urban lake nutrition level based on climate and socioeconomic index, the method comprising:
s10) acquiring satellite images aiming at urban lake areas;
S20) determining a long time sequence nutrition state index of the urban lake area based on the satellite image;
S30) determining climate indexes and socioeconomic indexes affecting the urban lake area;
S40) obtaining a prediction model based on a random forest model;
s50) carrying out urban lake nutrition state index prediction based on the prediction model, and generating a prediction result.
In one possible implementation manner, firstly, a satellite image aiming at a city lake area is acquired, in the embodiment of the invention, a hole lake in a middle China area can be selected as a research case, after the city lake area to be monitored is selected and determined, the satellite image is acquired, for example, a Google EARTH ENGINE (GEE) cloud platform can be used, a Landsat series satellite remote sensing reflectivity image provided by the acquisition platform is used as the satellite image to be analyzed, and due to good image quality, radiation correction and geometric correction operations are not required.
After the satellite images are acquired, the long-time-sequence nutrition state indexes of the urban lake area are further obtained. Referring to fig. 2, in an embodiment of the present invention, the determining the long time-series nutritional status index of the city lake region based on the satellite image includes:
s21) preprocessing the satellite image to obtain a preprocessed image;
s22) carrying out water analysis on the preprocessed image to generate a water analysis result;
s23) performing inversion operation of a long time sequence nutrition state index for the urban lake area based on the preprocessed image and the water body analysis result to obtain an inversion result;
s24) generating a long time-series nutritional status index of the city lake area based on the inversion result.
In one possible implementation manner, the satellite image is preprocessed, specifically, the satellite image may be a vector file of the border of the Dongting lake, after the file is obtained, all satellite remote sensing images in 2000 to 2022 are cut first, a cut image is obtained, then cloud removal processing is performed on the cut image, specifically, a "QA_PIXEL" band of "LANDSAT/LC09/C02/T1_L2" image is selected to perform cloud removal operation on the image, and a cloud removed image, that is, a preprocessed image is obtained.
At this time, water analysis is performed on the preprocessed image, and in the embodiment of the invention, a Normalized Difference Water Index (NDWI) is used for performing water extraction operation, and the calculation method of the normalized difference water index is specifically characterized as follows:
Wherein, R GREEN and R NIR are the remote sensing reflectivities of the green band and the near infrared band respectively.
And at the moment, further executing inversion operation of the long-time sequence nutrition state index aiming at the urban lake area according to the preprocessed image and the water body analysis result.
In the embodiment of the present invention, the performing an inversion operation for a long-time-series nutritional status index of a city lake area based on the preprocessed image and the water body analysis result, to obtain an inversion result, includes: performing nutrition state decomposition analysis on the water body analysis result based on a turbid water body extraction algorithm to obtain a first nutrition state area and a second nutrition state area; performing nutrition index analysis on the first nutrition status area based on a first preset algorithm to generate a first intermediate index, wherein the first preset algorithm is characterized in that: ; and carrying out nutrition index analysis on the second nutrition status area based on a second preset algorithm to generate a second intermediate index, wherein the second preset algorithm is characterized in that: ; wherein ABI OLI is characterized as an algae biomass index ABI calculated from OLI data in the pre-processed image, the algae biomass index ABI is characterized as: ; wherein R BLUE、RRED and R NIR are characterized as surface reflectance data of 485 nm, 660nm and 835nm for TM and etm+ spectra in the preprocessed image, respectively, and R BLUE、RRED and R NIR are 482nm, 655nm and 865nm for OLI images, respectively, lambda BLUE、λGREEN、λRED、λNIR is characterized as the center wavelength of each satellite's corresponding band; and performing lake inversion operation based on the first intermediate index and the second intermediate index to obtain an inversion result.
In a specific implementation process, the extracted water body (namely, a water body analysis result) can be decomposed and analyzed according to a turbid water body index (TWI) algorithm so as to divide the water body pixels into inorganic suspended matter-dominant water body pixels and algae-dominant water body pixels, wherein the TWI is specifically characterized in that: Wherein R SWIR is surface reflectivity data with TM and ETM+ spectrum wavelength of 1650nm, TWI thresholds of the TM, ETM+ and OLI sensors are respectively 0.083, 0.074 and 0.076 in the embodiment of the invention, namely, the water body which is smaller than the thresholds and is considered to be the dominant algae is larger than the water body which is mainly inorganic suspended matters.
Then, respectively carrying out inversion analysis on inorganic suspended matter dominant water pixels and algae dominant water pixels according to the first preset algorithm and the second preset algorithm by using a TSI inversion method of an OLI sensor to generate corresponding first intermediate indexes and second intermediate indexes, expanding the OLI-based algorithm to TM and ETM+, establishing a conversion relation between ABI TM、ABIETM+、ABIOLI and ABI MODIS by using a MODIS satellite image, and further calculating to obtainAndThe method is characterized by comprising the following steps:； . Namely, the calibration enables an OLI-based algorithm to be expanded to TM and ETM+ so as to realize lake inversion operation and obtain a corresponding inversion result. And finally, averaging all non-null values in the inversion result to calculate a long time sequence nutrition state index representing the urban lake area, namely a final TSI value. Then further determining the climate index and the socioeconomic index affecting the urban lake area.
Referring to fig. 3, in an embodiment of the present invention, the determining the climate index and the socioeconomic index affecting the city lake region includes:
S31) determining an initial climate index based on the lunar meteorological data of the urban lake area;
s32) acquiring agricultural parameters, population parameters and economic parameters corresponding to the urban lake area, and generating initial socioeconomic indexes based on the agricultural parameters, the population parameters and the economic parameters;
S33) analyzing the initial climate index and the initial socioeconomic index based on a Pearson correlation algorithm to generate a key climate index and a key socioeconomic index;
s34) screening the key climate indexes and the key socioeconomic indexes according to a preset screening rule to generate climate indexes and socioeconomic indexes of the urban lake area.
In one possible implementation manner, initial weather indexes are determined according to lunar meteorological data of urban lake areas, and as data indexes such as air temperature, rainfall, wind speed and wind direction serve as indexes capable of quantifying weather changes, lunar data of all cities related to the urban lake areas can be obtained from ERA5-Land data set issued by organizations such as European Union and European middle weather forecast centers and the like, and then the weather data corresponding to the cities are obtained by cutting according to city boundaries and taking an average value. And averaging the air temperature, the air speed and the air direction of each city, and adding the rainfall capacity of each city to obtain the initial climate index corresponding to the lake region of the city.
Then, related agricultural parameters, population parameters and economic parameters are obtained, wherein in the embodiment of the invention, the agricultural parameters can comprise, but are not limited to, agricultural land area, chemical fertilizer usage, pesticide usage and the like; population parameters may include, but are not limited to, parameters of general population, urbanization rate, population density, residential water usage, etc.; the economic parameters include, but are not limited to, a first industry increment value, a second industry increment value, a number of industrial enterprises above a scale, a consumption level index, an environmental protection investment to GDP ratio, and the like. In a specific implementation process, the socioeconomic indexes of each city are respectively added to obtain the initial socioeconomic index corresponding to the lake area of the city.
And then further analyzing the initial climate indexes and the initial socioeconomic indexes according to a Pearson correlation algorithm, and screening out key indexes influencing TSI of the urban lake area. At this time, a prediction model based on a random forest model is further acquired, and the model is generated by training a technician in advance.
In an embodiment of the present invention, the training the random forest model based on the long time-series nutrition state index, the climate index and the socioeconomic index to generate the prediction model includes: training the random forest model based on the long-time-sequence nutrition state index, the climate index and the socioeconomic index to obtain a preliminary training model; based on a preset parameter adjustment algorithm, carrying out parameter combination analysis on parameters of the preliminary training model, and outputting an optimal parameter combination; and adjusting the random forest model based on the optimal parameter combination to generate a prediction model.
In one possible implementation, the pixel average value of each existing data in the TSI inversion result of the urban lake area is determined as the TSI value of the urban lake area, and then the random forest model training is performed by taking the climate index and the socioeconomic index as independent variables and taking the TSI value as a dependent variable pair, so as to obtain a preliminary training model. Then optimizing the number of model estimators and the number of random states by using a simple search parameter tuning method, then searching the best parameter combination in a given parameter grid by using a GRIDSEARCHCV grid search parameter tuning method, specifically searching the best parameter combination in the grid parameter grids of the number of estimators, the maximum depth of the tree and the maximum feature number of each tree, and obtaining the best parameter combination. On the basis, the random forest model is adjusted to generate a prediction model, and then evaluation indexes on a training set and a test set are output. Finally, the training effect of the model can be determined by exhibiting the behavior of the model on the training set and the test set, as well as the scatter distribution between the predicted value and the actual value.
After the prediction model is obtained, the nutrition level of the urban lake area is predicted through the model so as to generate a prediction result. In the embodiment of the invention, the method for executing urban lake nutrition state index prediction based on the prediction model to generate a prediction result comprises the following steps: determining preset scene conditions; executing urban lake nutrition state index prediction based on the preset scenario conditions and the prediction model to generate an initial result; and classifying the nutritional state of the initial result based on the nutritional state classification standard to obtain a predicted result.
In one possible embodiment, scenario assumptions are made first when making nutrition level predictions. Specifically, future climate and social development situations can be set, and situation setting is performed according to the expected influence of the system and policy to be adopted on socioeconomic and climate, namely preset situation conditions are determined. For example, in this example, the trend of TSI of the fordiness lake is predicted within 5 years in a certain development stage in the future, and it is assumed that the total population in the future decreases by 1% per year, the annual increases of the first industry increase value and the second industry increase value are both 5%, and the annual increases of the industrial enterprises of the above scale are 1% (based on 2022 years of data). The temperature is increased by 0.5 ℃ compared with 2017-2022, and rainfall is also reduced by 1% as a whole.
The nutrient status classification criteria may be a determination of TSI <30 as nutrient-poor, 30.ltoreq.TSI <50 as nutrient-medium, 50.ltoreq.TSI <60 as nutrient-mild, 60.ltoreq.TSI <70 as nutrient-medium, and TSI >70 as nutrient-heavy.
On the basis, urban lake nutrition level prediction is carried out on future lakes through a prediction model, and the prediction results are combined with nutrition state grading standards to generate corresponding prediction results. For example, please refer to fig. 4, which is a schematic diagram of a prediction result under a set scenario according to an embodiment of the present invention.
According to the embodiment of the invention, the existing lake nutrition prediction method is improved, the prediction model with better prediction effect is trained by adopting satellite image data, and the lake nutrition level is predicted under the preset situation, so that the prediction complexity is effectively reduced, the prediction difficulty is greatly reduced, and the prediction accuracy and the prediction efficiency are improved.
The urban lake nutrition level prediction device based on the climate and socioeconomic indexes provided by the embodiment of the invention is described below with reference to the accompanying drawings.
Referring to fig. 5, based on the same inventive concept, an embodiment of the present invention provides an urban lake nutrition level prediction apparatus based on climate and socioeconomic index, the apparatus comprising: the image acquisition unit is used for acquiring satellite images aiming at urban lake areas; the index generation unit is used for determining a long-time-sequence nutrition state index of the urban lake area based on the satellite images; an index determining unit for determining a climate index and a socioeconomic index affecting the urban lake area; the model training unit is used for training a random forest model based on the long-time sequence nutrition state index, the climate index and the socioeconomic index to generate a prediction model; and the prediction unit is used for performing urban lake nutrition state index prediction based on the prediction model and generating a prediction result.
In an embodiment of the present invention, the index generating unit is specifically configured to: preprocessing the satellite image to obtain a preprocessed image; carrying out water analysis on the preprocessed image to generate a water analysis result; performing inversion operation of a long-time-sequence nutrition state index for the urban lake area based on the preprocessed image and the water body analysis result to obtain an inversion result; and generating a long-time-sequence nutrition state index of the urban lake area based on the inversion result.
In an embodiment of the present invention, the index determining unit is specifically configured to: determining an initial climate index based on the lunar meteorological data of the city lake region; acquiring agricultural parameters, population parameters and economic parameters corresponding to the urban lake area, and generating initial socioeconomic indexes based on the agricultural parameters, the population parameters and the economic parameters; analyzing the initial climate index and the initial socioeconomic index based on a pearson correlation algorithm to generate a key climate index and a key socioeconomic index; and screening the key climate indexes and the key socioeconomic indexes according to a preset screening rule to generate climate indexes and socioeconomic indexes of the urban lake area.
In an embodiment of the present invention, the model training unit is specifically configured to: training the random forest model based on the long-time-sequence nutrition state index, the climate index and the socioeconomic index to obtain a preliminary training model; based on a preset parameter adjustment algorithm, carrying out parameter combination analysis on parameters of the preliminary training model, and outputting an optimal parameter combination; and adjusting the random forest model based on the optimal parameter combination to generate a prediction model.
The foregoing details of the optional implementation of the embodiment of the present invention have been described in conjunction with the accompanying drawings, but the embodiment of the present invention is not limited to the specific details of the foregoing implementation, and various simple modifications may be made to the technical solution of the embodiment of the present invention within the scope of the technical concept of the embodiment of the present invention, where all the simple modifications belong to the protection scope of the embodiment of the present invention.
In addition, the specific features described in the above embodiments may be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, various possible combinations of embodiments of the present invention are not described in detail.
Those skilled in the art will appreciate that all or part of the steps in implementing the methods of the embodiments described above may be implemented by a program stored in a storage medium, including instructions for causing a single-chip microcomputer, chip or processor (processor) to perform all or part of the steps of the methods of the embodiments described herein. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In addition, any combination of various embodiments of the present invention may be performed, so long as the concept of the embodiments of the present invention is not violated, and the disclosure of the embodiments of the present invention should also be considered.
Claims (10)
1. A method for predicting urban lake nutrition level based on climate and socioeconomic index, comprising:
Acquiring satellite images aiming at urban lake areas;
determining a long-time-sequence nutritional state index of the urban lake area based on the satellite image;
determining a climate index and a socioeconomic index affecting the urban lake area;
Training a random forest model based on the long-time-sequence nutrition state index, the climate index and the socioeconomic index to generate a prediction model;
and executing urban lake nutrition state index prediction based on the prediction model to generate a prediction result.
2. The method of claim 1, wherein the determining a long-term nutritional status index for the city lake region based on the satellite imagery comprises:
preprocessing the satellite image to obtain a preprocessed image;
Carrying out water analysis on the preprocessed image to generate a water analysis result;
performing inversion operation of a long-time-sequence nutrition state index for the urban lake area based on the preprocessed image and the water body analysis result to obtain an inversion result;
And generating a long-time-sequence nutrition state index of the urban lake area based on the inversion result.
3. The method of claim 2, wherein the performing an inversion operation for a long-time-series nutritional status index of a city lake region based on the preprocessed image and the water body analysis result, obtaining an inversion result, comprises:
Performing nutrition state decomposition analysis on the water body analysis result based on a turbid water body extraction algorithm to obtain a first nutrition state area and a second nutrition state area;
Performing nutrition index analysis on the first nutrition status area based on a first preset algorithm to generate a first intermediate index, wherein the first preset algorithm is characterized in that:
；
and carrying out nutrition index analysis on the second nutrition status area based on a second preset algorithm to generate a second intermediate index, wherein the second preset algorithm is characterized in that:
；
Wherein ABI OLI is characterized as an algae biomass index ABI calculated from OLI data in the pre-processed image, the algae biomass index ABI is characterized as:
，
wherein R BLUE、RRED and R NIR are characterized as surface reflectance data of 485 nm, 660nm and 835nm for TM and etm+ spectra in the preprocessed image, respectively, and R BLUE、RRED and R NIR are 482nm, 655nm and 865nm for OLI images, respectively, lambda BLUE、λGREEN、λRED、λNIR is characterized as the center wavelength of each satellite's corresponding band;
and performing lake inversion operation based on the first intermediate index and the second intermediate index to obtain an inversion result.
4. The method of claim 1, wherein the determining the climate index and socioeconomic index affecting the city lake region comprises:
Determining an initial climate index based on the lunar meteorological data of the city lake region;
Acquiring agricultural parameters, population parameters and economic parameters corresponding to the urban lake area, and generating initial socioeconomic indexes based on the agricultural parameters, the population parameters and the economic parameters;
analyzing the initial climate index and the initial socioeconomic index based on a pearson correlation algorithm to generate a key climate index and a key socioeconomic index;
And screening the key climate indexes and the key socioeconomic indexes according to a preset screening rule to generate climate indexes and socioeconomic indexes of the urban lake area.
5. The method of claim 1, wherein the training a random forest model based on the long-time-series nutritional status index, the climate index, and the socioeconomic index to generate a predictive model comprises:
Training the random forest model based on the long-time-sequence nutrition state index, the climate index and the socioeconomic index to obtain a preliminary training model;
based on a preset parameter adjustment algorithm, carrying out parameter combination analysis on parameters of the preliminary training model, and outputting an optimal parameter combination;
and adjusting the random forest model based on the optimal parameter combination to generate a prediction model.
6. The method of claim 1, wherein the performing city lake nutritional state index prediction based on the predictive model generates a prediction result comprising:
Determining preset scene conditions;
executing urban lake nutrition state index prediction based on the preset scenario conditions and the prediction model to generate an initial result;
and classifying the nutritional state of the initial result based on the nutritional state classification standard to obtain a predicted result.
7. An urban lake nutrition level prediction device based on climate and socioeconomic indexes, comprising:
The image acquisition unit is used for acquiring satellite images aiming at urban lake areas;
The index generation unit is used for determining a long-time-sequence nutrition state index of the urban lake area based on the satellite images;
an index determining unit for determining a climate index and a socioeconomic index affecting the urban lake area;
The model training unit is used for training a random forest model based on the long-time sequence nutrition state index, the climate index and the socioeconomic index to generate a prediction model;
and the prediction unit is used for performing urban lake nutrition state index prediction based on the prediction model and generating a prediction result.
8. The apparatus according to claim 7, wherein the index generation unit is specifically configured to:
preprocessing the satellite image to obtain a preprocessed image;
Carrying out water analysis on the preprocessed image to generate a water analysis result;
performing inversion operation of a long-time-sequence nutrition state index for the urban lake area based on the preprocessed image and the water body analysis result to obtain an inversion result;
And generating a long-time-sequence nutrition state index of the urban lake area based on the inversion result.
9. The apparatus according to claim 7, wherein the index determination unit is specifically configured to:
Determining an initial climate index based on the lunar meteorological data of the city lake region;
Acquiring agricultural parameters, population parameters and economic parameters corresponding to the urban lake area, and generating initial socioeconomic indexes based on the agricultural parameters, the population parameters and the economic parameters;
analyzing the initial climate index and the initial socioeconomic index based on a pearson correlation algorithm to generate a key climate index and a key socioeconomic index;
And screening the key climate indexes and the key socioeconomic indexes according to a preset screening rule to generate climate indexes and socioeconomic indexes of the urban lake area.
10. The apparatus according to claim 7, wherein the model training unit is specifically configured to:
Training the random forest model based on the long-time-sequence nutrition state index, the climate index and the socioeconomic index to obtain a preliminary training model;
based on a preset parameter adjustment algorithm, carrying out parameter combination analysis on parameters of the preliminary training model, and outputting an optimal parameter combination;
and adjusting the random forest model based on the optimal parameter combination to generate a prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410763534.3A CN118332444B (en) | 2024-06-14 | 2024-06-14 | Urban lake nutrition level prediction method based on climate and socioeconomic index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410763534.3A CN118332444B (en) | 2024-06-14 | 2024-06-14 | Urban lake nutrition level prediction method based on climate and socioeconomic index |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118332444A true CN118332444A (en) | 2024-07-12 |
| CN118332444B CN118332444B (en) | 2024-08-20 |
Family
ID=91768230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410763534.3A Active CN118332444B (en) | 2024-06-14 | 2024-06-14 | Urban lake nutrition level prediction method based on climate and socioeconomic index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118332444B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106468658A (en) * | 2016-09-05 | 2017-03-01 | 中国科学院南京地理与湖泊研究所 | A kind of MODIS remote-sensing monitoring method of eutrophic lake phycocyanobilin |
| US20180262571A1 (en) * | 2016-03-04 | 2018-09-13 | Sabrina Akhtar | Integrated IoT (Internet of Things) System Solution for Smart Agriculture Management |
| CN110887790A (en) * | 2019-11-04 | 2020-03-17 | 华中科技大学 | Urban lake eutrophication simulation method and system based on FVCOM and remote sensing inversion |
| KR20200048898A (en) * | 2018-10-31 | 2020-05-08 | 강원대학교산학협력단 | Apparatus and method for analyzing dangerous of flooding or drought using machine-learning |
| KR20200128966A (en) * | 2019-05-07 | 2020-11-17 | 박해경 | Severe Drought Area Prediction Model based on Random Forest using Satellite Image & Topography Data |
| DE202022101031U1 (en) * | 2022-02-23 | 2022-03-08 | Hindustan Institute Of Technology & Science | A feedback and recommendation based system for evaluating urban architecture |
| CN116148188A (en) * | 2022-12-26 | 2023-05-23 | 江苏省苏力环境科技有限责任公司 | Air-space-ground integrated lake water quality tracing method, system, equipment and storage medium |
| CN117669392A (en) * | 2024-02-01 | 2024-03-08 | 自然资源部第二海洋研究所 | Remote sensing monitoring method for flux of nutrient salts of river |
-
2024
- 2024-06-14 CN CN202410763534.3A patent/CN118332444B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180262571A1 (en) * | 2016-03-04 | 2018-09-13 | Sabrina Akhtar | Integrated IoT (Internet of Things) System Solution for Smart Agriculture Management |
| CN106468658A (en) * | 2016-09-05 | 2017-03-01 | 中国科学院南京地理与湖泊研究所 | A kind of MODIS remote-sensing monitoring method of eutrophic lake phycocyanobilin |
| KR20200048898A (en) * | 2018-10-31 | 2020-05-08 | 강원대학교산학협력단 | Apparatus and method for analyzing dangerous of flooding or drought using machine-learning |
| KR20200128966A (en) * | 2019-05-07 | 2020-11-17 | 박해경 | Severe Drought Area Prediction Model based on Random Forest using Satellite Image & Topography Data |
| CN110887790A (en) * | 2019-11-04 | 2020-03-17 | 华中科技大学 | Urban lake eutrophication simulation method and system based on FVCOM and remote sensing inversion |
| DE202022101031U1 (en) * | 2022-02-23 | 2022-03-08 | Hindustan Institute Of Technology & Science | A feedback and recommendation based system for evaluating urban architecture |
| CN116148188A (en) * | 2022-12-26 | 2023-05-23 | 江苏省苏力环境科技有限责任公司 | Air-space-ground integrated lake water quality tracing method, system, equipment and storage medium |
| CN117669392A (en) * | 2024-02-01 | 2024-03-08 | 自然资源部第二海洋研究所 | Remote sensing monitoring method for flux of nutrient salts of river |
Non-Patent Citations (1)
| Title |
|---|
| 侯业楹;龙宇;李晓波;: "水库扩建工程水体富营养化预测评价方法研究", 环保科技, no. 05, 15 October 2013 (2013-10-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118332444B (en) | 2024-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tarwidi et al. | An optimized XGBoost-based machine learning method for predicting wave run-up on a sloping beach | |
| CN117290810B (en) | Short-time strong precipitation probability prediction fusion method based on cyclic convolutional neural network | |
| CN116699096B (en) | Water quality detection method and system based on deep learning | |
| CN113125383A (en) | Farming land secondary salinization monitoring and early warning method and system based on remote sensing | |
| CN112903606A (en) | Mangrove forest ecological restoration force assessment method based on unmanned aerial vehicle hyperspectrum | |
| CN111553289A (en) | Remote sensing image cloud detection method and system | |
| CN117030957A (en) | Remote sensing inversion method and system for offshore nutrient salt and chemical oxygen demand | |
| CN117710176B (en) | Ecological construction and restoration method and system for ecological sea wall oyster reef | |
| CN111523732A (en) | Japanese anchovy model screening and predicting method in winter | |
| CN111222748A (en) | Tuna habitat quantitative evaluation method | |
| CN118332444B (en) | Urban lake nutrition level prediction method based on climate and socioeconomic index | |
| CN117496369A (en) | Mining area carbon sink data set construction method | |
| CN116879192A (en) | Water bloom prediction method, device, equipment and medium based on satellite remote sensing data | |
| Liu et al. | Evaluation of the effectiveness of multiple machine learning methods in remote sensing quantitative retrieval of suspended matter concentrations: A case study of Nansi Lake in North China | |
| CN116089832A (en) | Method and device for reducing ground water reserves of gravity satellites and computer equipment | |
| KR102408840B1 (en) | Detecting method of water saturated weak area of forest soil for improving landslide danger map using forest water map and the system | |
| CN110751335B (en) | Regional ecological quality annual scene prediction evaluation method and device | |
| CN117909691B (en) | Ocean engineering design data acquisition system and method | |
| CN117828969B (en) | Satellite remote sensing earth surface temperature intelligent inversion method and system integrating DSM | |
| CN118072182B (en) | Red tide identification method, medium and system based on remote sensing image | |
| CN117408385A (en) | Improved cellular automaton cyanobacteria bloom prediction method | |
| CN118706090A (en) | Water depth prediction method for coastal waters | |
| Li et al. | Comprehensive Meteorological and Hydrological Drought Risks Under Changing Environment on the Wanquan River Basin, Southern China | |
| Leng et al. | Design of Forestry Carbon Sink Measurement and Prediction System Based on Convolutional Neural Network | |
| CN118070237A (en) | Lake water chlorophyll a concentration inversion method based on Sentinel-2 image |
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 |