Hybrid Deep Neural Architectures with Evolutionary Optimization and Explainable AI for Drought Susceptibility Assessment

This study presents a novel ensemble deep-learning framework integrating Convolutional Neural Networks (CNN), self-attention mechanisms, and Long Short-Term Memory (LSTM) networks, designed to generate high-resolution drought susceptibility maps for the Oroqen Autonomous Banner of Inner Mongolia. The model was further enhanced through two metaheuristic optimization techniques—Differential Evolution (DE) and Biogeography-Based Optimization (BBO)—which tuned hyperparameters including CNN filters, LSTM units, and learning rate. Model evaluation—quantified via predictive accuracy (RMSE = 0.22 and MAE = 0.12), goodness-of-fit (R2 = 0.79), and classification discrimination [Area Under the Receiver Operating Characteristic curve (AUROC) = 0.91]—revealed that the BBO-optimized ensemble achieved the best overall performance on the test set, outperforming the DE-enhanced (AUROC = 0.86) and baseline models (AUROC = 0.80). Pairwise z-statistics confirmed the statistical superiority of the BBO-enhanced ensemble with a p-value < 0.001. The final susceptibility map—classified into five levels using the Jenks natural breaks method—identified western rangelands and transitional ecotones as high-susceptibility zones, while eastern areas were marked by lower susceptibility. The resulting outputs offer decision-makers and land managers an interpretable, high-precision tool to guide drought preparedness, implement resource allocation strategies, and design early-warning systems. This research establishes a scalable, interpretable, and statistically robust approach for drought susceptibility assessment in vulnerable landscapes.