• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    The present invention provides a large-scale spatial distribution simulation method for soil arthropods, which also includes the simulation method: first obtaining the number of soil arthropods at each sampling point and a multi-source environmental variable that affects the distribution of the arthropods; then building a large-scale spatial distribution simulation model of the soil arthropods according to the number of soil arthropods at each sampling point and the multi-source environmental variable; and finally, acquiring a large-scale multi-source environmental variable of an area to be simulated and inputting the large-scale multi-source environmental variables of the area to be simulated into the large-scale spatial distribution simulation model of the soil arthropods in order to simulate the large-scale spatial distribution of the soil arthropods in the area to be simulated. The present invention realizes the large-scale spatial distribution simulation of the ground-dwelling arthropods, and the large-scale spatial distribution simulation of the ground-dwelling arthropods in a mining area can provide a better basis for ecological rehabilitation planning and management decision of the mining area and is a necessary means for evaluating the comprehensive management effect of hills, bodies of water , Forestry, fields, lakes and grasses within the mining area.
    公开号:CH716601A2
    申请号:CH01439/19
    申请日:2019-11-13
    公开日:2021-03-15
    发明作者:Bian Zhenxing；Guo Xiaoyu；Li Yan；Bi Jianping；Yu Miao；Wang Shuai；Wang Jianzhong；Liu Yonghai；Yang Siwen；Li Ying；Wang Zhibiao；Xu Wenda；Liu Minghua
    申请人:Univ Shenyang Agricultural；Jianping Shengde Rixin Mining Ltd Company；
    IPC主号:
    专利说明:

    description
    TECHNICAL PART
    The present invention relates to the technical field of ecological restoration of the impact assessment of a mining area, in particular to a large-scale spatial distribution simulation method for a soil arthropod.
    BACKGROUND
    The rich biodiversity offers many ecological functions and services for the ecological restoration of a mining area. Soil-dwelling arthropods are an important part of biodiversity. They have many species, high density, wide distribution, and short life cycle, and are indicative of species of biodiversity in ecosystems. The existing assessment methods use a square to collect soil arthropods, to examine the biodiversity of an ecological restoration zone in the mining area, to assess the ecological restoration effect and to analyze the evolutionary law of the ecological restoration of the mining area.
    Because of the difficulty in extracting the soil arthropods, there are problems such as long periods of time and large investments in manpower and financial resources. Currently, the square method can only be used on a small scale and the results only reflect the diversity of ground-dwelling arthropods in a property or area and cannot assess and reflect the overall effect of ecological restoration in a large mining area.
    SUMMARY
    The aim of the present invention is to provide a large-scale spatial distribution simulation method for a soil arthropod in order to realize a large-scale spatial distribution simulation of the soil arthropod and thus to reflect the overall effect of the ecological restoration of a large mining area.
    In order to achieve the above-mentioned purpose, the present invention offers the following technical solution.
    A large-scale spatial distribution simulation method for soil arthropods includes the following steps:
    Obtaining the number of soil arthropods at each sampling point and determining a multi-source environmental variable that affects the distribution of the arthropods;
    Creating a large-scale spatial distribution simulation model of the soil-dwelling arthropods according to the number of soil-dwelling arthropods at each sampling point and the multi-source environmental variables influencing the distribution of the arthropods;
    Acquiring a large-scale multi-source shared variable of an area to be simulated; and introducing the large-scale multi-source environmental variables of the area to be simulated into the large-scale spatial distribution simulation model of the ground-dwelling arthropods to simulate the large-scale spatial distribution of the ground-dwelling arthropods in the area to be simulated.
    Optionally, the creation of a large-scale spatial distribution simulation model of the ground-dwelling arthropods according to the number of ground-dwelling arthropods at each sampling point and the multi-source environmental variables that influence the distribution of the arthropods, in particular:
    Using a randomForest function to build a randomForest model with the number of soil arthropods as the explanatory variable and the multisource environment variable as the explanatory variable;
    Inputting the multi-source environment variable of each extraction point into the randomForest model to obtain a prediction result for each extraction point;
    Calculating a prediction error of the randomForest model on the basis of the number of arthropods living in the ground at each sampling point and the prediction result of each sampling point;
    Determining whether the prediction error of the randomForest model satisfies a prediction condition to obtain a first determination result;
    Outputting the randomForest model to obtain a large-scale spatial distribution simulation model of the soil arthropods when the first determination result indicates that the prediction error satisfies the prediction condition; and
    Updating a parameter of the randomForest model and returning to the step of inputting the multi-source environment variable of each sampling point to the randomForest model to obtain a prediction result of each sampling point when the first determination result indicates that the prediction error does not satisfy the prediction condition.
    Optionally, the calculation of a prediction error of the randomForest model on the basis of the number of soil arthropods at each sampling point and the prediction result of each sampling point specifically includes:
    Calculating a mean prediction error (mean absolute error MAE) for the number of soil arthropods and the prediction result using the formula ->. I
    Calculating a root mean square error (RMSE) of the number of arthropods living in the ground and the prediction result by the formula
    RMSE =
    Calculating a correlation coefficient R2 between the number of ground-dwelling arthropods and the prediction result by the formula
    V yy
    SLu- ) '
    Calculating a Lin's uniformity correlation coefficient (LUCC) of the number of soil arthropods and the prediction result by the formula un
    where xi and yi are the prediction result of the multi-source environmental variable of the i-th sampling point and the number of ground-dwelling arthropods at the i-th sampling point, respectively; n represents the number of sampling points; x and y are the mean values of the forecast results and the number of soil arthropods of the n sampling points; 8x2 and 9y2 are the variances of the forecast results and the number of soil arthropods of the n sampling points; dxdy is a covariance of the prediction results and the number of soil arthropods of the n sampling points; r is a Pearson correlation coefficient between the prediction result and the number of soil arthropods.
    Optionally, determining whether the prediction error of the randomForest model is less than a preset threshold value in order to obtain a first determination result specifically comprises:
    Determine whether the formula
    MAE <3t && RMSE <a2 && R2> a3 && LUCC> a4 is established or set up to obtain a second determination result;
    Determining that the first determination result is that the prediction error satisfies the prediction condition when the second determination result indicates that the formula
    MAE <3t && RMSE <a2 && R2> a3 && LUCC> a4 is set up; and
    Determining that the first determination result is that the prediction error does not satisfy the prediction condition when the second determination result indicates that the
    Formula MAE <a! && RMSE <a2 && R2> a3 && LUCC> a4 is not set up;
    where a! a2 ,,, a3, and a4 represent first, second, third and fourth preset thresholds, respectively.
    Optionally, the method includes prior to entering the multi-source environment variable of each sampling point or. Sample point in the randomForest model to obtain a prediction result for each sample point, continue with the following step:
    Performing a multi-collinearity test on the multi-source shared variables of all sample points and eliminating multi-collinear shared variables from the multi-source shared variables of the sample points to obtain tested multi-environmental variables.
    Optionally, after collecting a large-scale, multi-source environment variable of an area to be simulated, the method further includes the following step:
    Masking a raster map of the large area multi-source environment variable of the area to be simulated so that the grid data of the grid map of the large area multi-source environment variable of the area to be simulated all have the same determinant, and obtaining a masked grid map of the large area multi-source environment variable.
    According to the specific embodiments of the present invention, the present invention has the following technical effects.
    The present invention provides a large-scale spatial distribution simulation method for soil arthropods, which includes the simulation method: first obtaining the number of soil arthropods at each sampling point and a multi-source environment variable that affects the distribution of the arthropods; then building a large-scale spatial distribution simulation model of the soil arthropods according to the number of soil arthropods at each sampling point and the multi-source environmental variable that affects the distribution of the arthropods; and finally collecting large-scale multi-source environmental variables of an area to be simulated and inputting the large-scale multi-source environmental variables of the area to be simulated into the large-scale spatial distribution simulation model of soil arthropods to simulate the large-scale spatial distribution of soil arthropods in the area to be simulated. The present invention realizes that the large-scale spatial distribution simulation of the ground-dwelling arthropods, and the large-scale spatial distribution simulation of the ground-dwelling arthropods in a mining area can provide a better basis for ecological rehabilitation planning and a management decision of the mining area and is a necessary means for assessing the comprehensive management effect of Hills, bodies of water, forestry, fields, lakes and grasses within the mining area.
    BRIEF DESCRIPTION OF THE DRAWINGS
    In order to describe the technical solutions in the embodiments of the present invention or in the prior art more clearly, the accompanying drawings required to describe the embodiments are briefly presented below. The accompanying drawings in the following description show only some embodiments of the present invention, and a person skilled in the art can derive still other embodiments from the accompanying drawings of the present invention without any inventive effort.
    FIGURE 1 is a flow diagram of a large scale spatial distribution simulation method for a soil arthropod provided by the present invention; and
    FIGURE 2 is a schematic diagram of a large scale spatial distribution simulation method for a soil arthropod provided by the present invention.
    DETAILED DESCRIPTION
    In the following, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present invention. The described embodiments are only a part and not all possible embodiments of the present invention. All other embodiments obtained by a person skilled in the art on the basis of the embodiments of the present invention with no inventive step also fall within the scope of the present invention.
    The aim of the present invention is to provide a large-scale spatial distribution simulation method for a soil arthropod in order to realize a large-scale spatial distribution simulation of the soil arthropod and thus to reflect the overall effect of the ecological restoration of a large mining area.
    In order to make the above aim, the features and advantages of the present invention clearer and more understandable, the present invention will be described in more detail below with reference to the accompanying drawings and specific embodiments.
    As shown in FIG. 1 and FIG. 2, the present invention represents a large-scale spatial distribution simulation method for a soil arthropod, the simulation method including the following steps.
    Step 101, obtaining the number of ground-dwelling arthropods at each sampling point and a multi-source environmental variable that affects the distribution of the arthropods.
    (1) Collect the number of soil dwelling arthropods at each sampling site and the multi-source environmental variables that affect the distribution of the arthropods.
    The multi-source environmental variable of the present invention includes the climatic conditions of the mining area (temperature, precipitation, etc.), topographical conditions (slope, altitude, topographical wetness
    etc.), landscape pattern conditions (landscape diversity index, degree of landscape separation, landscape uniformity etc.) and factors such as cultivated area conditions.
    A trapping method is used to detect the ground-dwelling arthropods, i.e. three traps are set up at each sampling point, and an average value of the ground-dwelling arthropods in the three traps is used as the number of ground-dwelling arthropods at the sampling point, in order to avoid a collection error. The distance between the traps is usually more than 10 m; a trap or catch bottle uses a plastic cup made of polypropylene (pp) with a bottom diameter of 6 cm, an outer diameter of 10 cm and a height of 13 cm; the pp plastic cup is buried in the ground with a cup opening flush with the bottom surface; 150-200 ml of ethylene glycol solution (20%) and a drop of detergent are contained in the cup, and a cup lid is attached with three iron wires that are inserted into the ground around the pp plastic cup to prevent rain. The traps are withdrawn after being placed outdoors for 6 days and the bottom arthropods in the catch bottle are placed in a pre-numbered polyethylene (PE) bottle with 75% alcohol. The number and type of soil arthropods are counted.
    (2) Preprocessing the number of soil dwelling arthropods at each sampling site and the multi-source environmental variables that affect the distribution of the arthropods.
    The number of soil-dwelling arthropods at each sampling point has a one-to-one correspondence with the value of the multi-source environmental variable.
    A multicollinearity test is performed on the multi-source shared variables of all sample points, and multicollinear shared variables are removed from the multi-source shared variables of the sample points to obtain tested multi-shared variables. The multicollinearity between the environmental variables is tested for the value of a variance inflation factor; in the case of multicollinearity, the multicollinear environment variables are eliminated by step-by-step regression; otherwise the environment variables can be used for modeling.
    Step 102, building a large-scale spatial distribution simulation model of the soil-dwelling arthropods according to the number of soil-dwelling arthropods at each sampling site and the multi-source environmental variables that affect the distribution of the arthropods.
    In particular, including:
    Using a randomForest function to build a randomForest model with the number of soil arthropods as the explanatory variable and the multisource environment variable as the explanatory variable;
    Inputting the multi-source environment variable of each sample point into the randomForest model to obtain a prediction result for each sample point;
    Calculating a prediction error of the randomForest model according to the number of soil-dwelling arthropods at each sampling point and the prediction result of each sampling point;
    Determining whether the prediction error of the randomForest model satisfies a prediction condition to obtain a first determination result;
    Outputting the randomForest model to obtain a large-scale spatial distribution simulation model of the soil arthropods when the first determination result indicates that the prediction error satisfies the prediction condition; and
    If the first evaluation result indicates that the prediction error does not match the prediction condition, update a parameter of the randomForest model and return to the step "Input the multi-source environment variable of each sample point into the randomForest model to obtain a prediction result of each sample point", the following three Parameters need to be set: the number of decision trees (ntree) that determine the optimized randomForest classification model, the number of features that were randomly selected at each node within the decision tree (mtry), and the size of the leaf nodes (nodesize), the minimum Samples; in the R software, a default value is generally chosen for the node size, the initial ntree is selected using a plot function, and the parameter mtry is determined by sequentially increasing its value using 1 as the starting point (initial value) and 1 adjusted as the step size; ntree is updated using the plot function and the value of mtry is increased by 1.
    The "calculating a prediction error of the randomForest model according to the number of soil arthropods at each sampling point and the prediction result of each sampling point" includes in particular: Calculating an average prediction error (mean absolute error MAE) of the number of soil arthropods and the prediction result using the calculation formula root mean square error (RMSE)
    the number of arthropods living on the ground and the prediction result by the formula ■ '' -. To calculate
    a correlation coefficient between the R2 number of soil arthropods and the prediction result by the formula; Calculation of a Lin's uniformity correlation coefficient (LUCC) of the number of soil arthropods and the prediction result using the formula LUCC = "^, '*." Xwwwith xi and yi, the prediction result of the multi-source environmental variables of the i-th sampling point and the number of soil arthropods, respectively are the i-th sampling point; n represents the number of sampling points; x and y are the mean of the forecast results and the numbers of soil arthropods of the n sampling points; 3x2 and 3y2 are the variances of the forecast results and the numbers of soil arthropods of the n sampling points; dxdy is a covariance of the prediction results and the numbers of soil arthropods of the n sampling points; r is a Pearson correlation coefficient between the prediction result and the number of soil arthropods. The “determining whether the prediction error of the randomForest model satisfies a prediction condition in order to obtain a first determination result” includes in particular: determining whether the formula MAE <a! && RMSE <a2 && R2> a3 && LUCC> a4 is useful for obtaining a second determination result; When the second determination result indicates that the formula MAE <a! && RMSE <a2 && R2> a3 && LUCC> a4 is useful, determining whether the first determination result is that the prediction error satisfies the prediction condition, and determining that the first determination result is that the prediction error does not satisfy the prediction condition when the second determination result indicates that the formula MAE <
    && RMSE <a2 && R2> a3 && LUCC> a4 is not useful, where a, a2 ,,, a3 and a4 represent first, second, third and fourth preset thresholds, respectively. That is, the present invention checks the mean prediction error (MAE), mean square error (RMSE), correlation coefficient (R2) and uniformity correlation coefficient (LUCC) of the Lin according to the four verification indices; if the model accuracy is poor, the parameter setting process is repeated, and if the model accuracy is good, the training of randomForest is completed.
    Step 103, acquiring a large area multi-source environment variable of an area to be simulated.
    A raster map of the large area multi-source environment variable of the area to be simulated is masked so that the grid data of the grid map of the large area multi-source environment variable of the area to be simulated all have the same determinant, and a masked grid map of the large area multi-source environment variable is obtained.
    In particular, a masking and extraction tool from ArcGIS is used to mask and extract two of the environment variables from one another and then mask and extract the other environment variables according to a prepared mask to ensure that the determinants of all environment variable raster maps are completely identical; in the R Software, coordinates and data values corresponding to the large multi-source environment variables of the same determinant form a data frame, and the raster data frame is read using a raster packet in the R software.
    Step 104, inputting the large-scale multi-source environmental variables of the area to be simulated into the large-scale spatial distribution simulation model of the soil-dwelling arthropods to simulate the large-scale spatial distribution of the soil-dwelling arthropods in the area to be simulated. A spatial distribution map of the soil arthropod is output using a writeRaster function in the R software in order to complete the spatial distribution of the soil arthropods in the ecological restoration of the large mining area.
    According to the specific embodiments of the present invention, the present invention has the following technical effects.
    The modeling process of the present invention does not have to specify a verification set for the verification, but takes over the cross-verification. The spatial distribution of the soil-dwelling arthropods in the ecological restoration of the large mining area is simulated by a small amount of measurement data in combination with corresponding multi-source environmental variables that reflect the ecological restoration capacity and the potential of the mining area from the perspective of biodiversity and a basis for the ecological restoration of the Mining area can form.
    The foregoing merely describes a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto. One skilled in the art can easily devise changes or substitutions in the technical field of the present invention, but these changes or substitutions fall within the scope of the present invention.
    Several examples are used to illustrate the principles and methods of practicing the present invention. The description of the embodiments serves to illustrate the device and its core concept in the present invention. In addition, those of ordinary skill in the art can make various modifications in terms of specific implementation methods and areas of application in accordance with the concept of the present invention. In summary, it can be said that the content of this description should not be interpreted as a restriction of the present invention.
    权利要求:
    Claims (6)
    [1]
    1. A method for simulating the large-scale distribution for soil arthropods, the simulation method comprising the following steps:
    Obtaining the number of soil arthropods at each sampling site and determining a multi-source environmental variable that affects the distribution of the arthropods;
    Creating a large-scale spatial distribution simulation model of the soil-dwelling arthropods according to the number of soil-dwelling arthropods at each sampling point and the multi-source environmental variables influencing the distribution of the arthropods;
    Acquiring a large-scale multi-source shared variable of an area to be simulated; andintroducing the large-scale multi-source environmental variables of the area to be simulated into the large-scale spatial distribution simulation model of the ground-dwelling arthropods in order to simulate the large-scale spatial distribution of the ground-dwelling arthropods in the area to be simulated.
    [2]
    2. The method for simulating the large-scale spatial distribution for soil arthropods according to claim 1, wherein the creation of a large-scale spatial distribution simulation model of the soil arthropods on the basis of the number of soil arthropods at each extraction point and the multi-source environment variables influencing the distribution of the arthropods comprises in particular:
    Using a randomForest function to build a randomForest model with the number of soil arthropods as the explanatory variable and the multisource environment variable as the explanatory variable;
    Inputting the multi-source environment variable of each extraction point into the randomForest model to obtain a prediction result for each extraction point;
    Calculating a prediction error of the randomForest model according to the number of arthropods living in the ground at each sampling point and the prediction result of each sampling point;
    Determining whether the prediction error of the randomForest model satisfies a prediction condition to obtain a first determination result;
    Outputting the randomForest model to obtain a large-scale spatial distribution simulation model of the soil arthropods when the first determination result indicates that the prediction error satisfies the prediction condition; and
    Updating a parameter of the randomForest model and returning to the step of inputting the multi-source environment variable of each sample point to the randomForest model to obtain a prediction result of each sample point when the first determination result indicates that the prediction error does not satisfy the prediction condition.
    [3]
    3. The large-scale spatial distribution simulation method for soil arthropods according to claim 2, wherein calculating a prediction error of the randomForest model according to the number of soil arthropods at each sampling point and the prediction result of each sampling point comprises:
    Calculating a mean prediction error (mean absolute error MAE) of the number of soil arthropods and the prediction result by the formula MAE = ig.l | x1-yL |;
    Calculating a root mean square error (RMSE) of the number of arthropods living in the ground and the prediction result by the formula RMSE
    Calculating a correlation coefficient R2 between the number of ground-dwelling arthropods and the prediction result by the formula
    Calculating a Lin's Uniformity Correlation Coefficient (LUCC) of the number of soil arthropods and the prediction result by the formula
    wherein xi and yi are the prediction result of the multi-source environmental variable of the i-th sampling point and the number of ground-dwelling arthropods at the i-th sampling point, respectively; n represents the number of sampling points; x and y are the mean values of the forecast results and the numbers of soil arthropods of the n sampling points; 3x2 and 3y2 are the variances of the forecast results and the number of soil arthropods of the n sampling points; dxdy is a covariance of the prediction results and the number of soil arthropods of the n sampling points; r is a Pearson correlation coefficient between the prediction result and the number of soil arthropods.
    [4]
    4. The method of simulating the large-scale distribution for soil arthropods according to claim 3, wherein determining whether the prediction error of the randomForest model satisfies a prediction condition to obtain a first determination result comprises:
    Determine whether the formula MAE <a! && RMSE <a2 && R2> a3 && LUCC> a4 is set up to obtain a second determination result;
    Determining that the first determination result is that the prediction error satisfies the prediction condition when the second determination result indicates that the formula MAE <3t && RMSE <a2 && R2> a3 && LUCC> a4 is established; and
    When the second determination result indicates that the formula MAE <a! && RMSE <a2 && R2> a3 && LUCC> a4 is not set up;
    where a! a2 ,,, a3 and a4 each represent a first preset threshold, a second preset threshold, a third preset threshold, and a fourth preset threshold.
    [5]
    5. The method for simulating the large-scale distribution for soil arthropods according to claim 2, further comprising the following step prior to inputting the multi-source environment variable of each sampling point into the randomForest model to obtain a prediction result for each sampling point:
    Performing a multi-collinearity test on the multi-source shared variables of all sample points and eliminating multi-collinear shared variables from the multi-source shared variables of the sample points to obtain tested multi-environmental variables.
    [6]
    The method of simulating large-scale distribution for soil arthropods according to claim 1, further comprising the step of after acquiring a large-scale multi-source environmental variable of an area to be simulated:
    Masking a raster map of the large area multi-source environment variable of the area to be simulated so that the grid data of the grid map of the large area multi-source environment variable of the area to be simulated all have the same determinant, and obtaining a masked grid map of the large area multi-source environment variable.
    类似技术:
    公开号 | 公开日 | 专利标题
    Berger et al.2006|Creating agents and landscapes for multiagent systems from random samples
    Balent et al.1992|Modelling bird communities/landscape patterns relationships in a rural area of South-Western France
    Singh2010|Robust parameter estimation in gauged and ungauged basins
    Diéguez-Aranda et al.2006|Site quality curves for birch stands in north-western Spain
    Grech et al.2013|On the multifractal effects generated by monofractal signals
    Rashed2012|Assessing degree of karstification: a new method of classifying karst aquifers
    DE112015006900T5|2018-05-24|Method for determining online NIR sample sizes
    DE112014006799T5|2017-05-11|Method for measuring a user behavior consistency level based on a complex correspondence system
    DE102017129299A1|2019-06-13|Method for local weather forecast
    CN103793054B|2016-08-17|A kind of action identification method simulating declarative memory process
    CN109840873A|2019-06-04|A kind of Cross Some Region Without Data Hydro-Model Parameter Calibration Technology fields method based on machine learning
    CH716601A2|2021-03-15|Method to simulate the large-scale distribution for ground-dwelling arthropods.
    CN109615627A|2019-04-12|A kind of power transmission and transformation inspection image quality evaluating method and system
    CN109242203A|2019-01-18|A kind of water quality prediction of river and water quality impact factors assessment method
    Lin et al.2011|Identifying the spatial mixture distribution of bird diversity across urban and suburban areas in the metropolis: A case study in Taipei Basin of Taiwan
    RAKHSHANDEHROO et al.2010|Flood forecasting in similar catchments using neural networks
    DE112018004567T5|2020-06-04|Spectral analysis device and spectral analysis method
    Ellis1996|The application of machine learning techniques to erosion modelling
    Huber2019|Towards robust projections of future forest dynamics: why there is no silver bullet to cope with complexity
    Evans et al.1996|Integrating remotely sensed data with other spatial data sets to predict areas at risk from salinity
    CN110232334A|2019-09-13|A kind of steel construction corrosion recognition methods based on convolutional neural networks
    Chen et al.2021|A partially confirmatory approach to scale development with the Bayesian Lasso.
    DE102019115293A1|2020-02-27|Flow analysis optimization device and method therefor
    DE102020201183A1|2021-08-05|Method and device for simulating a technical system
    DE102020201605A1|2021-08-12|Computer-implemented method and device for machine learning
    同族专利:
    公开号 | 公开日
    CH716601A8|2021-05-14|
    CN110837911B|2021-02-05|
    CN110837911A|2020-02-25|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    GB2434225A|2006-01-13|2007-07-18|Cytokinetics Inc|Random forest modelling of cellular phenotypes|
    CN104572786A|2013-10-29|2015-04-29|华为技术有限公司|Visualized optimization processing method and device for random forest classification model|
    CN105631526A|2014-10-31|2016-06-01|航天恒星科技有限公司|Forest pest disease outbreak risk prediction method and device|
    CN106611079B|2016-11-07|2020-01-10|水利部交通运输部国家能源局南京水利科学研究院|Individual mode-based fish motion and spatial distribution simulation method and system|
    CN106980750B|2017-02-23|2019-10-29|中国科学院南京土壤研究所|A kind of Soil Nitrogen estimation method of reserve based on typical correspondence analysis|
    CN108388566B|2017-06-15|2021-07-27|中国科学院地理科学与资源研究所|Spatial simulation method for abundance distribution of plant species|
    US11263707B2|2017-08-08|2022-03-01|Indigo Ag, Inc.|Machine learning in agricultural planting, growing, and harvesting contexts|
    CN108984995A|2018-09-28|2018-12-11|同济大学|A kind of ecology garden landscape design method of evaluation simulation|
    法律状态:
    2021-03-31| PK| Correction|Free format text: BERICHTIGUNG INHABER |
    2021-05-14| PK| Correction|Free format text: BERICHTIGUNG A8 |
    2021-12-15| AZW| Rejection (application)|
    优先权:
    申请号 | 申请日 | 专利标题
    CN201910841804.7A|CN110837911B|2019-09-06|2019-09-06|Large-scale ground surface arthropod space distribution simulation method|
    [返回顶部]