CN116705144A - Method for measuring correlation between species distribution data and environmental factors - Google Patents
Method for measuring correlation between species distribution data and environmental factors Download PDFInfo
- Publication number
- CN116705144A CN116705144A CN202310986013.XA CN202310986013A CN116705144A CN 116705144 A CN116705144 A CN 116705144A CN 202310986013 A CN202310986013 A CN 202310986013A CN 116705144 A CN116705144 A CN 116705144A
- Authority
- CN
- China
- Prior art keywords
- species
- model
- distribution
- data
- species distribution
- 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
- 238000009826 distribution Methods 0.000 title claims abstract description 93
- 230000007613 environmental effect Effects 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 25
- 241000894007 species Species 0.000 claims abstract description 84
- 240000007164 Salvia officinalis Species 0.000 claims abstract description 36
- 235000005412 red sage Nutrition 0.000 claims abstract description 30
- 238000012549 training Methods 0.000 claims abstract description 18
- 230000000694 effects Effects 0.000 claims abstract description 16
- 239000002689 soil Substances 0.000 claims abstract description 9
- 238000012876 topography Methods 0.000 claims abstract description 9
- 238000011160 research Methods 0.000 claims abstract description 5
- 235000014166 Salvia virgata Nutrition 0.000 claims abstract description 4
- 238000012795 verification Methods 0.000 claims abstract description 3
- 238000007637 random forest analysis Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 244000132619 red sage Species 0.000 claims description 11
- 235000011135 Salvia miltiorrhiza Nutrition 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 7
- 238000011835 investigation Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 241000196324 Embryophyta Species 0.000 claims description 5
- 235000017276 Salvia Nutrition 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000013210 evaluation model Methods 0.000 claims description 3
- 238000009614 chemical analysis method Methods 0.000 claims 1
- 230000002596 correlated effect Effects 0.000 claims 1
- 230000024053 secondary metabolic process Effects 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000003066 decision tree Methods 0.000 description 9
- 239000000463 material Substances 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 238000005096 rolling process Methods 0.000 description 4
- 230000010354 integration Effects 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 241000282412 Homo Species 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 238000013138 pruning Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 241000207923 Lamiaceae Species 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000003110 anti-inflammatory effect Effects 0.000 description 1
- 230000003064 anti-oxidating effect Effects 0.000 description 1
- 230000010100 anticoagulation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 235000002020 sage Nutrition 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B5/00—ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
- G16B5/20—Probabilistic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B50/00—ICT programming tools or database systems specially adapted for bioinformatics
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Medical Informatics (AREA)
- Biotechnology (AREA)
- Databases & Information Systems (AREA)
- Physiology (AREA)
- Molecular Biology (AREA)
- Bioethics (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for measuring correlation between species distribution data and environmental factors, which belongs to the field of biological geography research, and comprises the following steps: s1: referring to known species distribution information, establishing a salvia species distribution model, and positioning the species model; the red sage species model positioning adopts longitude and latitude mode positioning for repeated and misoperation points; s2: analyzing through the correlation between the species distribution model and the environment variable; wherein the environmental variables include: climate, soil, topography and human activity; s3: based on environment variables in the S2, ten common species distribution models are selected, and training and verification models are carried out on a modeling platform; the method can be realized by adopting a modeling platform to build a model of the correlation between environmental factors and species distribution, training and analyzing the species, and summarizing relevant beneficial information of the red sage root in the planting area of China.
Description
Technical Field
The invention relates to the field of biological geography research, in particular to a method for measuring species distribution data and correlating environmental factors.
Background
The red sage is one of the common important medicinal materials in China, is perennial upright herb of the red sage group of the sage of the Labiatae, is used as a medicament with dry roots and rhizomes, has the effects of antioxidation, anticoagulation, anti-inflammatory and the like, and is clinically applied to the treatment of cardiovascular diseases. The extremely high medicinal value causes the demand of the red sage root to be continuously increased, and the huge demand causes the red sage root to be widely introduced and cultivated, and more than 90% of commercial red sage root comes from artificial planting.
However, due to regional environment limitation, the current red sage root has larger yield difference in each region and uneven quality, which affects the clinical application effect and is unfavorable for the development of red sage root. And developing the suitable living area of medicinal materials, exploring the suitable performance of the Chinese medicinal materials and the ecological environment to find the environment and the corresponding geographic space which are more suitable for the growth of the medicinal materials, avoiding blind planting, and having important practical significance for improving the quality of the medicinal materials and realizing the sustainable development of the medicinal materials.
The investigation shows that the research for planting the red sage root in the geographic position is not available at present, the investigation of the red sage root before planting is usually judged according to factors such as climate, topography, traffic, humanity and the like, the investigation mode can be basically carried out only in a very small range nationwide, the obtained planting information is limited, blind planting is easy to cause, and the improvement of the quality of medicinal materials is not facilitated.
Disclosure of Invention
1. Technical problem to be solved
Aiming at the problems existing in the prior art, the invention aims to provide a method for measuring the correlation between species distribution data and environmental factors, which can be realized by adopting a modeling platform to establish a model for correlating the environmental factors with species distribution, training and analyzing the species and summarizing relevant beneficial information of the red sage root in the planting area of China.
2. Technical proposal
In order to solve the problems, the invention adopts the following technical scheme.
A method of measuring species distribution data associated with an environmental factor, comprising the steps of:
s1: referring to known species distribution information, establishing a salvia species distribution model, and positioning the species model;
the red sage species model positioning adopts longitude and latitude mode positioning for repeated and misoperation points;
s2: analyzing through the correlation between the species distribution model and the environment variable;
wherein the environmental variables include: climate, soil, topography and human activity;
s3: based on environment variables in the S2, ten common species distribution models are selected, a modeling platform is used for training and verifying the models, and ten common species training data are obtained by adopting a random function algorithm;
s4: verifying the model precision, and analyzing the influence of environmental variables on species distribution;
s5: the prediction model is potential spatial distribution in China and suitable for living environment.
Further, in the step S1, the known species distribution information approach can be obtained from any one of field investigation, a global biodiversity information network database or a China digital plant specimen library;
wherein, any one of a maximum entropy model, a random forest and a generalized linear model is adopted for the species model building platform; in modeling the distribution of the species of red sage root and modeling the environmental variables, a form of single model building can be utilized, and the single model building further comprises: surface distribution distinguishing chamber model, flexible discriminant analysis, classification tree analysis, push type regression tree and artificial neural network.
And if some species positioning information has errors, the repeated or misoperation places can be deleted, grid points are selected by using longitude and latitude information to avoid excessive fitting of the model, and only a single point is reserved in each 1km grid point, so that 270 salvia miltiorrhiza points are obtained.
Further, in the step S2, the environment variable data information includes:
the climate information is acquired from a world climate database;
soil data are obtained from the national Qinghai-Tibet plateau data center;
the topography is obtained from a national basic geographic information system database;
human activities are obtained from NASA earth observations, which can observe migration traces of humans for nearly twenty years;
the spatial resolution of all environmental factors is kept the same and is 30' (-1 km), the high correlation among biological climate variables can influence the precision and the prediction result of the model, the correlation among any one test data of a maximum entropy model, a random forest and a generalized linear model is adopted, for obviously related variables, the variables with small contribution to the distribution of the red sage root are removed by a knife cutting method, and finally, the model with the correlation between the environmental factors and the distribution of the species is established by a modeling platform, and the larger the real skill statistical value is, the stronger the correlation between the distribution model of the red sage root and the environmental variables is, and the higher the precision of the prediction result is.
In step S3, the training data of ten common species are represented by using any index evaluation model of the area under the curve and the true skill statistic.
Further, in S4, the dominant factors affecting the distribution of the root of red-rooted salvia include: low temperature for warm months, average potential evapotranspiration for cold seasons, potential evapotranspiration for years, month change in potential evapotranspiration, and high temperature for cold months;
and secondly human activity and altitude.
Further, in the step S5, the prediction result of the combined model of the distribution of the species of the salvia miltiorrhiza and the environmental variable effectively indicates the potential spatial distribution of the salvia miltiorrhiza in China and the suitable living environment, and the suitable growth area of the salvia miltiorrhiza is mainly in the subtropical to warm temperate climate zone of China under the current climate environment.
3. Advantageous effects
Compared with the prior art, the invention has the advantages that:
(1) According to the method, the relevance between species distribution information and environment variables is analyzed, so that a species distribution and environment variable combination model is established, the planting effect and planting information of the red sage root in the whole country can be accurately analyzed and predicted, the probability of blind planting of the red sage root is reduced, and the medicinal value and medicinal material quality of the red sage root are improved.
(2) According to the method, factors of environment variables on the planting of the red sage root are analyzed, and four aspects of climate, soil, topography and human activities are aimed at, so that the potential space distribution of the red sage root in China and the suitable living environment can be effectively described, and powerful help is provided for the planting of the red sage root.
Drawings
FIG. 1 is a diagram showing statistics of the overall area of a suitable area of Salvia Miltiorrhiza;
wherein, the a graph part is a broken line statistical graph of the ratio of the radix salviae miltiorrhizae suitable region;
and part b is an overall histogram of the distribution of the red sage root in different suitable areas.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention; it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments, and that all other embodiments obtained by persons of ordinary skill in the art without making creative efforts based on the embodiments in the present invention are within the protection scope of the present invention.
Examples:
referring to fig. 1, a method for correlating species distribution data with environmental factors includes the steps of:
s1: referring to known species distribution information, establishing a salvia species distribution model, and positioning the species model;
positioning the salvia miltiorrhiza species model, namely positioning points with repeated and wrong places in a longitude and latitude mode;
s2: analyzing through the correlation between the species distribution model and the environment variable;
wherein the environment variables include: climate, soil, topography and human activity;
s3: based on environment variables in the S2, ten common species distribution models are selected, and training and verification models are carried out on a modeling platform; ten common species training data are obtained by using a random function algorithm, and a species distribution model is to correlate distribution data of known species with environmental factors, predict actual distribution and potential distribution of the species on a certain spatial and time scale, simulate the actual niche of the species, and estimate the contribution of environmental variables.
S4: verifying the model precision, and analyzing the influence of environmental variables on species distribution;
s5: the prediction model is potential spatial distribution in China and suitable for living environment.
The ecological niche model is widely applied to simulating the distribution of species, and based on the ecological niche theory, such as the concepts of a space ecological niche, a functional ecological niche and a basic ecological niche, the ecological demand of the species is calculated according to a certain algorithm by utilizing the distribution data of the known species and related environmental variables, and then the calculation result is projected to different spaces and time to predict the actual distribution and the potential distribution of the species; the ecological niche model of this scheme is based on environmental factors associated with species distribution points to infer ecological needs of the species and simulate the distribution of the species.
S1, referring to a known species distribution information path, the species distribution information path can be obtained from any one of field investigation, a global biodiversity information network database or a China digital plant specimen library;
wherein, any one of a maximum entropy model, a random forest and a generalized linear model is adopted for the species model building platform; in modeling the distribution of the species of red sage root and modeling the environmental variables, a form of single model building can be utilized, and the single model building further comprises: surface distribution distinguishing chamber model, flexible discriminant analysis, classification tree analysis, push type regression tree and artificial neural network.
And if some species positioning information has errors, the repeated or misoperation places can be deleted, grid points are selected by using longitude and latitude information to avoid excessive fitting of the model, and only a single point is reserved in each 1km grid point, so that 270 salvia miltiorrhiza points are obtained.
Referring to tables 1 and 2 below, S2, the environment variable data information includes:
the climate information is acquired from a world climate database;
soil data are obtained from the national Qinghai-Tibet plateau data center;
the topography is obtained from a national basic geographic information system database;
human activities are obtained from NASA earth observations, which can observe migration traces of humans for nearly twenty years;
the spatial resolution of all environmental factors is kept the same and is 30' (-1 km), the high correlation among biological climate variables can influence the precision and the prediction result of the model, the correlation among any one test data of a maximum entropy model, a random forest and a generalized linear model is adopted, the variable with obvious correlation is removed by a knife cutting method, and the model with small contribution degree to the distribution of the salvia miltiorrhiza is finally established by a modeling platform.
Table 1: a percentage statistics table of environmental variable data information;
table 2: a statistical graph of each factor of the environment variable data information;
the maximum entropy principle can be easily understood through a dice rolling test, a dice is rolled on the same tabletop for a plurality of times (the total rolling times are recorded as N), the average value of the N rolling results is known as [ mu ] (supposing [ mu ] =5.5), no more information exists for the dice and the rolling process, and the number of times of occurrence of six faces of the dice is known. Assuming now that the six faces 1,2, … occur with a number of occurrences of N1, N2, …, N6, respectively, with a corresponding probability of pi=ni/N, and that the test result of interest is the vector n= (N1, N2, …, N6) or the vector p= (p 1, p2, …, p 6), this test result corresponds to a large number of possible "implementations". Taking n=3, for example, the result of 3 throws is that two 6 points occur, one 2 points, then n= (0,1,0,0,0,2), but this N corresponds to 3 possible "implementations: the 2 points appear in the first, second and third throws, respectively. The number of implementation modes corresponding to the vector n is as follows according to the simple permutation and combination knowledge:
the algorithm principle of random forest also comprises decision tree:
the largest feature of the decision tree is intuitionistic and easy to explain. It is also used unintentionally or intentionally at a certain moment in the life of a person; the decision tree algorithm can be classified into an ID3 algorithm, a C4.5 algorithm and a CART algorithm according to different modes of feature selection. In the CART algorithm, the Gini index is used as feature selection, the feature with the smallest Gini index and the corresponding segmentation point are selected as the optimal feature and the optimal segmentation point, and the cycle is repeated until the stop condition is met.
Because the decision tree hardly makes any assumption on the training data, the tree structure can freely grow according to the characteristics of the training data without adding task constraint, and the percentage accuracy is reached. In order to improve the generalization capability of the decision tree, the decision tree uses a pruning method. Pruning reduces model variance while also reducing model bias. The integration of multiple decision trees (CART trees) using bagging is called random forest.
The effective precondition of the bagging integration method is that the base models must keep low correlation, the difference between the base models can be guaranteed only by the low correlation, and the base models with the difference can be combined together to form a stronger model.
In order to make CART trees have larger diversity, the random forest introduces additional randomness, namely feature randomness, in the generation of the tree in addition to the random oversampling of the samples and the increase of the randomness of the training set. In tree generation, the best feature of randomly sampled features is selected as the splitting node, thus making each tree more diverse.
Algorithm process of random forest:
input: training set D with data size of m and T CART trees output: a final random forest f (x);
a. performing m times of random oversampling on the training set D to obtain a sampling set Dsample with a sample size of m;
b. randomly selecting k attribute features from all attribute features, and selecting the best segmentation attribute feature as a node to construct a CART tree T (x);
c. repeating the above two steps for T times, namely establishing T decision trees;
d. the T decision trees form a random forest. If the classification algorithm predicts, the voting data finally belong to which category; in the case of regression prediction, the output of the final model is obtained by averaging.
Generalized linear model: is an extension of simple least squares regression (OLS) in which the response variable is continuous numerical data and obeys normal distribution, and the relationship between the expected value of the response variable and the predicted variable is a linear relationship. While the generalized linear model relaxes its assumption that the response variable may be a positive integer or classification data in the first place, which is distributed as some family of exponential distributions. And the relation between the function (connection function) of the expected value of the response variable and the predicted variable is linear. Thus, in GLM modeling, it is necessary to specify the distribution type and the connection function.
By adopting the modeling platforms, the statistical information of the distribution data and the environment variables of the species can be used according to the actual situation, different data are subjected to single analysis on different modeling platforms, the summarized conclusion data are summarized, and the data after screening training are used for establishing a model, so that the statistics among the data variables is convenient to follow-up, and the effect of obviously improving the prediction result and the distribution data precision is achieved;
overall, combining models improves prediction accuracy by aggregating the results of the individual models is a more desirable approach.
In S3, ten common species training data are expressed by adopting any index evaluation model of area under a curve and real skill statistics values, and the larger the real skill statistics values are, the stronger the correlation between the salvia miltiorrhiza distribution model and environment variables is, and the higher the accuracy of a prediction result is.
In S4, dominant factors affecting distribution of the root of red-rooted salvia include: low temperature for warm months, average potential evapotranspiration for cold seasons, potential evapotranspiration for years, month change in potential evapotranspiration, and high temperature for cold months;
secondly, human activities and altitude; different environmental factors act on the distribution of species at different spatial scales, and interactions among the species are often weakened at relatively large scales, so that climate variables play a main role, and excessive environmental variables easily increase the dimension of an ecological space, thereby being unfavorable for prediction of a model.
Among them, climate change is one of the main factors affecting the geographical distribution of plant species and vegetation patterns and structures, the global temperature is increasing, and the emission of greenhouse gases is also increasing dramatically. Climate change can lead to an increase in temperature and precipitation, which will also have a significant impact on the distribution of medicinal plants, climate, pest management, forest ecosystems, etc.;
the species distribution model is an extremely important tool for exploring the related ecological problems between species and environment under the global change background, is widely applied to planning and research of the influence of climate change on species distribution and a protection area, is based on an R language developed species distribution integrated prediction platform, can comprehensively evaluate the current species, predicts the species in a model with better integration accuracy, and further improves the accuracy of the model and the accuracy of predicting future species distribution to the greatest extent.
Referring to fig. 1, S5, the combined model prediction result of the distribution of the species of the red sage root and the environmental variables effectively illustrates the potential spatial distribution and the suitable living environment of the red sage root in china, and in the current climate environment, the suitable growth area of the red sage root is mainly in the subtropical to warm temperature zone climate zone of China, the temperature and the potential evaporation amount are the main environmental factors influencing the distribution of the red sage root, and the areas of the provinces such as Hubei, shandong, henan, shanxi and Anhui are larger from the aspect of the area of the most suitable distribution area. The provinces of Hunan, hubei, guizhou, henan, jiangxi and Shandong are large in suitable area, the ratio of the suitable area to the total area of the provinces is more than 80%, the suitable area of Chongqing city and Zhejiang province is not high, but the suitable area of the suitable area is about 90% of the province, the total suitable area of Sichuan is high, but the ratio of the total area of the province is small, and the ratio is concentrated in the eastern part of Sichuan province.
The above description is only of the preferred embodiments of the present invention; the scope of the invention is not limited in this respect. Any person skilled in the art, within the technical scope of the present disclosure, may apply to the present invention, and the technical solution and the improvement thereof are all covered by the protection scope of the present invention.
Claims (8)
1. A method of measuring species distribution data associated with an environmental factor, characterized by: the method comprises the following steps:
s1: referring to known species distribution information, establishing a salvia species distribution model, and positioning the species model;
the red sage species model positioning adopts longitude and latitude mode positioning for repeated and misoperation points;
s2: analyzing through the correlation between the species distribution model and the environment variable;
wherein the environmental variables include: climate, soil, topography and human activity;
s3: based on environment variables in the S2, ten common species distribution models are selected, and training and verification models are carried out on a modeling platform;
s4: verifying the model precision, and analyzing the influence of environmental variables on species distribution;
s5: the prediction model is potential spatial distribution in China and suitable for living environment.
2. A method of measuring species distribution data in association with environmental factors as claimed in claim 1 wherein: in the S1, referring to a known species distribution information path, the species distribution information path can be obtained from any one of field investigation, a global biodiversity information network database or a China digital plant specimen library;
any one of a maximum entropy model, a random forest and a generalized linear model is adopted for the species model building platform;
if some species positioning information has errors, the repeated or error sites can be deleted, and only a single site is reserved in each 1km grid point, so that 270 salvia miltiorrhiza sites are obtained.
3. A method of measuring species distribution data in association with environmental factors as claimed in claim 1 wherein: in the step S2, the environment variable data information includes:
the climate information is acquired from a world climate database;
soil data are obtained from the national Qinghai-Tibet plateau data center;
the topography is obtained from a national basic geographic information system database;
the spatial resolution of all environmental factors is kept the same, the high correlation among biological climate variables can influence the precision and the prediction result of the model, the correlation among any one test data of a maximum entropy model, a random forest and a generalized linear model is adopted, the variable with small contribution to the distribution of the salvia miltiorrhiza is removed by a knife cutting method for the obviously correlated variable, and finally a modeling platform is adopted to establish a model of the correlation between the environmental factors and the species distribution.
4. A method of measuring species distribution data in association with environmental factors as claimed in claim 1 wherein: in the step S3, ten common species training data are represented by adopting any index evaluation model of area under a curve and true skill statistical values.
5. A method of measuring species distribution data in association with environmental factors as claimed in claim 1 wherein: in the step S4, dominant factors affecting distribution of the root of red-rooted salvia include: low temperature in warm months, average potential evapotranspiration in cold seasons, annual potential evapotranspiration, month change in potential evapotranspiration, high temperature in cold months, human activity and altitude.
6. A method of measuring species distribution data in association with environmental factors as claimed in claim 1 wherein: in the step S5, a chemical analysis method is added into a prediction model to research the relationship data between the physicochemical properties and the inorganic element content of the red sage root soil in different producing areas, and the prediction model obtains a conclusion: temperature is a major factor in determining distribution of red sage root, and also has an effect on secondary metabolism of red sage root.
7. A method of measuring species distribution data in association with environmental factors as claimed in claim 3 wherein: in modeling the distribution of the species of red sage root and modeling the environmental variables, a form of single model building can be utilized, and the single model building further comprises: surface distribution distinguishing chamber model, flexible discriminant analysis, classification tree analysis, push type regression tree and artificial neural network.
8. A method of measuring species distribution data in association with environmental factors as claimed in claim 4 wherein: ten common species training data were obtained using a random function algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310986013.XA CN116705144A (en) | 2023-08-07 | 2023-08-07 | Method for measuring correlation between species distribution data and environmental factors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310986013.XA CN116705144A (en) | 2023-08-07 | 2023-08-07 | Method for measuring correlation between species distribution data and environmental factors |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116705144A true CN116705144A (en) | 2023-09-05 |
Family
ID=87841748
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310986013.XA Pending CN116705144A (en) | 2023-08-07 | 2023-08-07 | Method for measuring correlation between species distribution data and environmental factors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116705144A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117647968A (en) * | 2024-01-29 | 2024-03-05 | 深圳益实科技有限公司 | Remote intelligent diagnosis and analysis system for faults of vehicle-mounted display screen |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN218470719U (en) * | 2022-09-26 | 2023-02-10 | 四川省农村经济综合信息中心 | Road medicinal material soil detection device |
-
2023
- 2023-08-07 CN CN202310986013.XA patent/CN116705144A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN218470719U (en) * | 2022-09-26 | 2023-02-10 | 四川省农村经济综合信息中心 | Road medicinal material soil detection device |
Non-Patent Citations (3)
| Title |
|---|
| 王茹琳;王明田;罗家栋;刘原;吴世权;文刚;李庆;: "基于MaxEnt模型的美味猕猴桃在中国气候适宜性分析", 云南农业大学学报(自然科学), no. 03 * |
| 高瑜等: "基于组合模型的丹参潜在地理分布研究", 《植物科学学报》, pages 3 - 579 * |
| 高铭;倪淑萍;沈亮;: "基于MaxEnt模型的丹参全球潜在生态适宜产区分析", 中国药房, no. 16 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117647968A (en) * | 2024-01-29 | 2024-03-05 | 深圳益实科技有限公司 | Remote intelligent diagnosis and analysis system for faults of vehicle-mounted display screen |
| CN117647968B (en) * | 2024-01-29 | 2024-04-26 | 深圳益实科技有限公司 | Remote intelligent diagnosis and analysis system for faults of vehicle-mounted display screen |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wei et al. | Predicting the current and future cultivation regions of Carthamus tinctorius L. using MaxEnt model under climate change in China | |
| Schellenberger Costa et al. | Community‐weighted means and functional dispersion of plant functional traits along environmental gradients on Mount Kilimanjaro | |
| Cardelús et al. | Vascular epiphyte distribution patterns: explaining the mid-elevation richness peak | |
| CN108877905B (en) | Hospital outpatient quantity prediction method based on Xgboost framework | |
| Malanson et al. | Dispersal probability and forest diversity in a fragmented landscape | |
| Du et al. | Phylogenetic constraints and trait correlates of flowering phenology in the angiosperm flora of C hina | |
| Box | Macroclimate and plant forms: an introduction to predictive modeling in phytogeography | |
| Solomon et al. | Computer-aided reconstruction of late-Quaternary landscape dynamics | |
| Cai et al. | Global models and predictions of plant diversity based on advanced machine learning techniques | |
| Shi et al. | Prediction of the potentially suitable areas of Litsea cubeba in China based on future climate change using the optimized MaxEnt model | |
| Latifah et al. | Evaluation of Random Forest model for forest fire prediction based on climatology over Borneo | |
| CN116705144A (en) | Method for measuring correlation between species distribution data and environmental factors | |
| Tang et al. | How climate change will alter the distribution of suitable Dendrobium habitats | |
| Freeman et al. | Drivers of plant functional group richness and beta diversity in fire‐dependent pine savannas | |
| Zhang et al. | Environmental filtering and spatial processes shape the beta diversity of liana communities in a valley savanna in southwest China | |
| Tang et al. | Potential distribution of the extremely endangered species Ostrya rehderiana (Betulaceae) in China under future climate change | |
| Yang et al. | Predicting the Potential Distribution of the Endangered Plant Magnolia wilsonii Using MaxEnt under Climate Change in China. | |
| Gorel et al. | Climatic niche lability but growth form conservatism in the African woody flora | |
| Flores-Tolentino et al. | Biogeographic regionalization by spatial and environmental components: Numerical proposal | |
| Wang et al. | Habitat suitability modeling based on remote sensing to realize time synchronization of species and environmental variables | |
| Jinga et al. | Dry and wet miombo woodlands of south-central Africa respond differently to climate change | |
| CN113128871B (en) | Cooperative estimation method for larch distribution change and productivity under climate change condition | |
| Karakaya et al. | Potential distribution modelling and mapping of dog rose (Rosa canina L.) in the nur mountains of gazİantep district, turkey | |
| Singh | Crop growth simulation models | |
| Li et al. | Impact of spin-up forcing on vegetation states simulated by a dynamic global vegetation model coupled with a land surface model |
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 |