Biodiversity estimation by environment drivers using machine/deep learning for ecological management

Abstract

Biodiversity is a crucial indicator of the health and resilience of ecosystems. Accurate estimation and prediction of biodiversity can support effective ecological management practices. This study aimed to estimate and predict biodiversity based on Environmental Factors (EFs), using Machine Learning (ML) including Deep Learning (DL) algorithms. First, the importance of EFs, including Mean Annual Precipitation (MAP), slope, aspect, and elevation, in influencing biodiversity was evaluated using Minimum Redundancy Maximum Relevance (MRMR) and Recursive Feature Elimination with Relief Feature Selection (RReliefF), and their correlations with multi-spatial biodiversity indices were analyzed. Our findings revealed that MAP was the most important environmental variable in estimating biodiversity, followed by slope, aspect, and elevation. Next, the ability of four ML algorithms (multiple linear regression, decision tree, random forest, support vector machine) and a deep neural network (DNN) to estimate biodiversity was evaluated by the coefficient of determination (r-square) and the root-mean-square error (RMSE) metrics. The DNN model achieved the highest accuracy (r-square: 0.884) among the ML algorithms and was further optimized to determine the optimal level of model complexity. These findings highlight the potential of DNN to effectively estimate biodiversity and suggest that using EF features with DL algorithms can improve our understanding of the relationships between environmental drivers and biodiversity, providing valuable insights for conservation and management decision-making towards sustainable development.