Analysis of Spatiotemporal Characteristics of Global TCWV and AI Hybrid Model Prediction

Extreme precipitation events severely impact agriculture, reducing yields and land use efficiency. The spatiotemporal distribution of Total Column Water Vapor (TCWV), the primary gaseous form of water, directly influences sustainable agricultural management. This study, through multi-source data fusion, employs methods including the Mann–Kendall test, sliding change-point detection, wavelet transform, pixel-scale trend estimation, and linear regression to analyze the spatiotemporal dynamics of global TCWV from 1959 to 2023 and its impacts on agricultural systems, surpassing the limitations of single-method approaches. Results reveal a global TCWV increase of 0.0168 kg/m²/year from 1959–2023, with a pivotal shift in 2002 amplifying changes, notably in tropical regions (e.g., Amazon, Congo Basins, Southeast Asia) where cumulative increases exceeded 2 kg/m² since 2000, while mid-to-high latitudes remained stable and polar regions showed minimal content. These dynamics escalate weather risks, impacting sustainable agricultural management with irrigation and crop adaptation. To enhance prediction accuracy, we propose a novel hybrid model combining wavelet transform with LSTM, TCN, and GRU deep learning models, substantially improving multidimensional feature extraction and nonstationary trend capture. Comparative analysis shows that WT-TCN performs the best (MAE = 0.170, R² = 0.953), demonstrating its potential for addressing climate change uncertainties. These findings provide valuable applications for precision agriculture, sustainable water resource management, and disaster early warning.