Method for predicting proper growth environment of Chinese galangal based on MaxEnt model

Abstract

The invention discloses a method for predicting a proper growth environment of Chinese galangal based on a MaxEnt model, and the method comprises the following steps: S1, obtaining natural distribution site data of the Chinese galangal, and obtaining effective distribution sites of the Chinese galangal; s2, optimizing an adjustment frequency multiplier and characteristic combination parameters of the MaxEnt model to obtain an optimized MaxEnt model; s3, environment factors of the effective distribution sites are obtained, the Spearman correlation analysis is used for calculating the correlation relation of the environment factors, the environment factors are screened through the optimized MaxEnt model and ArcGIS software, and key environment factors with the large contribution rate to the Chinese galangal are selected; s4, inputting the key environment factors into the optimized MaxEnt model for calculation and analysis, and processing the key environment factors through ArcGIS software to obtain a prediction result; and S5, performing accuracy evaluation on the prediction result, performing suitability grading by utilizing ArcGIS according to the evaluation result, and visually displaying suitability distribution of the Chinese galangal in different areas.

Description

Technical Field

[0001] This application relates to the technical field of predicting the suitable growing environment for Chinese galangal, and in particular to a method for predicting the suitable growing environment for Chinese galangal based on the MaxEnt model. Background Technology

[0002] Chinese galangal (Alpinia officinarum) is a plant of significant economic, medicinal, and ornamental value. Its rhizomes are rich in gingerol, flavonoids, and volatile oils, possessing antioxidant, anti-inflammatory, and antibacterial properties. It is widely used in traditional Chinese medicine, food, and health products, and as a spice in the food processing industry. Furthermore, galangal has a beautiful plant shape, vibrant green leaves, and unique inflorescences, making it highly valued for its ornamental qualities and commonly used in landscaping in tropical and subtropical regions. However, environmental changes have significantly impacted the distribution pattern of galangal. Therefore, researching its suitable habitat distribution under current environmental conditions is crucial for germplasm resource conservation and the sustainable development of its horticultural applications.

[0003] The MaxEnt model is widely used for species distribution prediction, but its default parameters may lead to overfitting or underfitting, which in turn affects the prediction accuracy. In addition, multicollinearity of environmental variables can also affect the prediction performance of the MaxEnt model.

[0004] Therefore, in order to address the problems existing in the above-mentioned technologies, a method for predicting the suitable growth environment of Chinese galangal based on the MaxEnt model is proposed. Summary of the Invention

[0005] This application provides a method for predicting the suitable growing environment of Chinese galangal based on the MaxEnt model, in order to solve the technical problems that the existing MaxEnt model overfits or underfits in predicting the suitable growing environment of Chinese galangal, thus affecting the prediction accuracy, and that the multicollinearity of environmental factors also affects the prediction effect of the MaxEnt model.

[0006] In view of this, this application provides a method for predicting the suitable growing environment of Chinese galangal based on the MaxEnt model, including the following steps:

[0007] S1. Obtain natural distribution site data of Chinese galangal, and perform geographical filtering on the natural distribution site data to obtain the effective distribution sites of Chinese galangal.

[0008] S2. Optimize the adjustment multiplier and feature combination parameters of the MaxEnt model to obtain the optimized MaxEnt model;

[0009] S3. Obtain the environmental factors of the effective distribution sites, calculate the correlation between the environmental factors using Spearman correlation analysis, and then screen the environmental factors using the optimized MaxEnt model and ArcGIS software to select the key environmental factors that have a high contribution rate to Alpinia galanga in China.

[0010] S4. Input the key environmental factors into the optimized MaxEnt model for calculation and analysis, and then process them through the ArcGIS software to obtain the prediction results;

[0011] S5. Evaluate the accuracy of the prediction results, and use ArcGIS to perform suitability classification based on the evaluation results, so as to intuitively display the suitability distribution of Chinese galangal in different regions.

[0012] Optionally, in step S3, the specific steps for selecting the key environmental factors that contribute significantly to the growth of Alpinia galanga in China are as follows:

[0013] The effective distribution site data was converted into CSV format, and the environmental factor data was converted into ASC format using ArcToolbox in ArcGIS model. The data were then imported into MaxEnt software for modeling and calculation. 25% of the effective distribution site data was selected for model validation, and 75% of the effective distribution site data was used to build the model. The knife cut method was used to detect the importance of the environmental factor data. The results were output in Logistic format, and environmental factors with a contribution of 0 in the calculation results were discarded.

[0014] Correlation analysis was performed on environmental factors with non-zero contribution rates. The Spearman correlation coefficient ρ between two environmental factors was calculated. When the correlation coefficient |ρ|>0.8, only one environmental factor with a high contribution rate was selected, thus obtaining the key environmental factors with a high contribution rate to Alpinia galanga in China.

[0015] Optionally, the correlation coefficient calculation formula for the Spearman correlation analysis is as follows:

[0016]

[0017] Where ρ is the correlation coefficient. It is the difference in rank between two environmental factors, where n is the number of observations.

[0018] Optionally, in step S3, the parameters of the frequency multiplier are increased by 0.5 in increments of 0.5 within the range of 0.5 to 4, and the feature combination is set with six feature combinations.

[0019] Optionally, the key environmental factors include climate factors, topographic factors, and soil factors.

[0020] Optionally, in step S5, the method for evaluating the accuracy of the prediction result is as follows: the accuracy of the prediction result is evaluated based on the magnitude of the AUC value in the prediction result. When the AUC value is between 0.5 and 0.6, it indicates modeling failure; between 0.6 and 0.7, it indicates unreliable prediction result; between 0.7 and 0.8, it indicates a mediocre prediction result; between 0.8 and 0.9, it indicates a good prediction result; and between 0.9 and 1, it indicates an accurate prediction result.

[0021] Optionally, the method for suitability classification using ArcGIS includes the following steps:

[0022] Convert ASC files to raster files using ArcGIS and import administrative region maps simultaneously;

[0023] The reclassify command was then used to reclassify the suitable habitat of Alpinia galanga in China, dividing the habitat of Alpinia galanga in the study area into unsuitable habitat (P<0.2), poorly suitable habitat (0.2≤P<0.4), moderately suitable habitat (0.4≤P<0.6), and highly suitable habitat (0.6≤P≤1).

[0024] The spatial distribution of Alpinia galanga in China was obtained by statistically analyzing the areas of four suitable habitat zones.

[0025] As can be seen from the above technical solutions, the embodiments of this application have the following advantages:

[0026] This application provides a method for predicting the suitable growing environment of Chinese galangal based on the MaxEnt model. This method further filters environmental factors using the optimized MaxEnt model and ArcGIS software, selecting key environmental factors that contribute significantly to the growth of Chinese galangal, avoiding interference from non-key environmental factors, reducing multicollinearity among environmental factors and the risk of model overfitting. Spearman correlation analysis is used to calculate the correlation between environmental factors, further reducing multicollinearity and overfitting. The MaxEnt model parameters are optimized, significantly improving the accuracy and stability of the MaxEnt model in predicting suitable habitats for Chinese galangal. Therefore, this method more accurately reflects the distribution pattern and habitat requirements of Chinese galangal under current environmental conditions, providing a reliable scientific basis for the protection of Chinese galangal germplasm resources, its application in landscaping, and scientific cultivation decisions, thus contributing to its adaptive management and sustainable utilization in the face of environmental changes. Attached Figure Description

[0027] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a flowchart illustrating the steps of a method for predicting the suitable growing environment of Alpinia galanga in China based on the MaxEnt model, as provided in an embodiment of this application.

[0029] Figure 2 This is a schematic diagram of Spearman correlation analysis of 28 environmental factors for a method to predict the suitable growth environment of Chinese galangal based on the MaxEnt model provided in the embodiments of this application.

[0030] Figure 3 This is a schematic diagram of the AICc graphical optimization results of a method for predicting the suitable growth environment of Chinese galangal based on the MaxEnt model provided in the embodiments of this application.

[0031] Figure 4 This is a schematic diagram of the environmental factor response curves under the optimized parameter MaxEnt model and the default parameter MaxEnt model, which is provided in the embodiments of this application for predicting the suitable growth environment of Chinese galangal based on the MaxEnt model.

[0032] Figure 5 This is a schematic diagram of the AUC value of a method for predicting the suitable growing environment of Chinese galangal based on the MaxEnt model provided in the embodiments of this application. Detailed Implementation

[0033] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0034] For easier understanding, please refer to Figures 1 to 5 This invention provides a method for predicting the suitable growing environment of Chinese galangal based on the MaxEnt model, comprising the following steps:

[0035] S1. Obtain natural distribution site data of Chinese galangal, and perform geographic filtering on the natural distribution site data to obtain the effective distribution sites of Chinese galangal.

[0036] Specifically, the data on the natural distribution points of Alpinia galanga in China comes from the Global Biodiversity Information Network database and the China Digital Herbarium, obtaining information on 1,500 distribution sites worldwide. Using ArcGIS software, distribution sites outside of China were removed, resulting in 75 valid distribution sites for Alpinia galanga across the country.

[0037] S2. Optimize the adjustment multiplier and feature combination parameters of the MaxEnt model to obtain the optimized MaxEnt model;

[0038] Specifically, the ENMeval software package was used to optimize the parameters of the tuning multiplier (RM) and feature combination (FC) of the MaxEnt model to improve the model's prediction accuracy. Specifically, the tuning multiplier parameter was increased by 0.5 in increments of 0.5 within the range of 0.5 to 4. Six feature combinations (including linear features, quadratic features, fragmented features, etc.) were set, and the optimal combination was selected from the six feature combinations using the delta value of the Akaike minimum information criterion correction value (AICc). This achieved an optimal balance between the complexity and fitness of the MaxEnt model, and RM = 4.0 and FC = L were determined as the optimal parameter combination under the current environmental conditions. Figure 3 As shown.

[0039] S3. Obtain environmental factors of effective distribution sites, calculate the correlation between environmental factors using Spearman correlation analysis, and then screen the environmental factors using the optimized MaxEnt model and ArcGIS software to select the key environmental factors that have a high contribution rate to Chinese galangal.

[0040] Specifically, the effective distribution site data was converted into CSV format, and the environmental factor data was converted into ASC format using ArcToolbox in the ArcGIS model. These were then imported into the MaxEnt model for calculation. 25% of the effective distribution site data was selected for model validation, and 75% of the effective distribution site data was used to build the model. The knife-cut method was used to detect the importance of the environmental factor data. The results were output in Logistic format, and environmental factors with a contribution of 0 were discarded, resulting in 28 environmental factors with a contribution of non-zero.

[0041] Spearman correlation analysis was performed on 28 environmental factors with non-zero contribution rates to reduce the impact of multicollinearity and ensure the stability and predictive performance of the MaxEnt model. The Spearman correlation coefficient ρ between two environmental factors was calculated. When the correlation coefficient |ρ| > 0.8, only one environmental factor with a high contribution rate was selected, resulting in 11 key environmental factors with significant contributions to Alpinia galanga in China. Specifically, the formula for calculating the correlation coefficient in the Spearman correlation analysis is as follows:

[0042]

[0043] Where ρ is the correlation coefficient. It is the difference in rank between two environmental factors, where n is the number of observations.

[0044] Furthermore, the key environmental factors include four climatic factors (such as annual maximum temperature, seasonal variation of annual mean temperature, seasonal variation of precipitation, and precipitation in the driest quarter), three topographic factors (such as altitude, aspect, and slope), and four soil factors (such as clay content, gravel content, organic carbon content, and soil pH). These key environmental factors reflect the main habitat requirements of Alpinia galanga in China under current environmental conditions.

[0045] S4. Input the key environmental factors into the optimized MaxEnt model for calculation and analysis, and then process them using ArcGIS software to obtain the prediction results, such as... Figure 4 As shown, the red curve represents the MaxEnt model after parameter optimization;

[0046] S5. Evaluate the accuracy of the prediction results and use ArcGIS to classify the suitability based on the evaluation results, so as to intuitively display the suitability distribution of Chinese galangal in different regions.

[0047] Specifically, the accuracy of the prediction results is evaluated based on the AUC value. An AUC between 0.5 and 0.6 indicates modeling failure; between 0.6 and 0.7 indicates unreliable predictions; between 0.7 and 0.8 indicates moderate predictions; between 0.8 and 0.9 indicates good predictions; and between 0.9 and 1 indicates accurate predictions. Using the parameters RM=4.0 and FC=L, the optimized MaxEnt model was run 10 times, resulting in a predicted AUC value of 0.989 for the current environmental scenario. Figure 5 As shown, the Maxent model is reliable in predicting the suitable growing areas of Chinese galangal in China.

[0048] Furthermore, the ASC file is converted into a raster file using ArcGIS, and an administrative region map is imported simultaneously.

[0049] The reclassify command was then used to reclassify the suitable habitat of Alpinia galanga in China, dividing the habitat of Alpinia galanga in the study area into unsuitable habitat (P<0.2), poorly suitable habitat (0.2≤P<0.4), moderately suitable habitat (0.4≤P<0.6), and highly suitable habitat (0.6≤P≤1).

[0050] Further statistical analysis of the areas of four suitable habitat zones yielded the spatial distribution results of *Alpinia galanga* in China. Under the current environmental and climate scenario, the most suitable habitat areas for *Alpinia galanga* in China are mainly distributed in central and southern Yunnan, central and southern Guizhou, southwestern Sichuan, southeastern Tibet, and most of Hainan. Under future environmental and climate scenarios, the suitable habitat area for *Alpinia galanga* will gradually expand, spreading from southern my country northward, with the total suitable habitat area exceeding the predicted area under the current environmental and climate scenario.

[0051] The above predictions accurately reflect the distribution pattern and habitat requirements of Alpinia galanga under the current environmental and climatic conditions, providing a reliable scientific basis for the protection of Alpinia galanga germplasm resources, its application in landscaping, and scientific cultivation decisions.

[0052] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0053] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for predicting the suitable growing environment of Alpinia galanga in China based on the MaxEnt model, characterized in that, Includes the following steps: S1. Obtain natural distribution site data of Chinese galangal, and perform geographical filtering on the natural distribution site data to obtain the effective distribution sites of Chinese galangal. S2. Optimize the adjustment multiplier and feature combination parameters of the MaxEnt model to obtain the optimized MaxEnt model; S3. Obtain the environmental factors of the effective distribution sites, calculate the correlation between the environmental factors using Spearman correlation analysis, and then screen the environmental factors using the optimized MaxEnt model and ArcGIS software to select the key environmental factors that have a high contribution rate to Alpinia galanga in China. S4. Input the key environmental factors into the optimized MaxEnt model for calculation and analysis, and then process them through the ArcGIS software to obtain the prediction results; S5. Evaluate the accuracy of the prediction results, and use ArcGIS to perform suitability classification based on the evaluation results, so as to intuitively display the suitability distribution of Chinese galangal in different regions.

2. The method for predicting the suitable growing environment of Alpinia galanga in China based on the MaxEnt model according to claim 1, characterized in that, In step S3, the specific steps for selecting the key environmental factors that contribute significantly to the growth of Alpinia galanga in China are as follows: The effective distribution site data was converted into CSV format, and the environmental factor data was converted into ASC format using ArcToolbox in ArcGIS model. The data were then imported into MaxEnt software for modeling and calculation. 25% of the effective distribution site data was selected for model validation, and 75% of the effective distribution site data was used to build the model. The knife cut method was used to detect the importance of the environmental factor data. The results were output in Logistic format, and environmental factors with a contribution of 0 in the calculation results were discarded. Correlation analysis was performed on environmental factors with non-zero contribution rates. The Spearman correlation coefficient ρ between two environmental factors was calculated. When the correlation coefficient |ρ|>0.8, only one environmental factor with a high contribution rate was selected, thus obtaining the key environmental factors with a high contribution rate to Alpinia galanga in China.

3. The method for predicting the suitable growing environment of Chinese galangal based on the MaxEnt model according to claim 2, characterized in that... The formula for calculating the correlation coefficient in the Spearman correlation analysis is as follows: Where ρ is the correlation coefficient. It is the difference in rank between two environmental factors, where n is the number of observations.

4. The method for predicting the suitable growing environment of Alpinia galanga in China based on the MaxEnt model according to claim 1, characterized in that, In step S3, the parameters of the frequency multiplier are increased by 0.5 in increments of 0.5 within the range of 0.5 to 4, and six feature combinations are set.

5. The method for predicting the suitable growing environment of Alpinia galanga in China based on the MaxEnt model according to claim 1, characterized in that, The key environmental factors include climate factors, topographic factors, and soil factors.

6. The method for predicting the suitable growing environment of Alpinia galanga in China based on the MaxEnt model according to claim 1, characterized in that, In step S5, the method for evaluating the accuracy of the prediction result is as follows: the accuracy of the prediction result is evaluated based on the magnitude of the AUC value in the prediction result. When the AUC value is between 0.5 and 0.6, it indicates modeling failure; between 0.6 and 0.7, it indicates unreliable prediction result; between 0.7 and 0.8, it indicates a mediocre prediction result; between 0.8 and 0.9, it indicates a good prediction result; and between 0.9 and 1, it indicates an accurate prediction result.

7. The method for predicting the suitable growing environment of Alpinia galanga in China based on the MaxEnt model according to claim 1, characterized in that, The steps of the method for performing suitability classification using ArcGIS are as follows: Convert ASC files to raster files using ArcGIS and import administrative region maps simultaneously; The reclassify command was then used to reclassify the suitable habitat of Alpinia galanga in China, dividing the habitat of Alpinia galanga in the study area into unsuitable habitat (P<0.2), poorly suitable habitat (0.2≤P<0.4), moderately suitable habitat (0.4≤P<0.6), and highly suitable habitat (0.6≤P≤1). The spatial distribution of Alpinia galanga in China was obtained by statistically analyzing the areas of four suitable habitat zones.

Images