Understanding spatiotemporal variations in forest cover is crucial for effective forest resource management. However, existing models often lack accuracy in simultaneously capturing temporal continuity and spatial correlation. To address this challenge, we developed ResConvLSTM-Att, a novel hybrid model integrating residual neural networks, Convolutional Long Short-Term Memory (ConvLSTM) networks, and attention mechanisms. We evaluated ResConvLSTM-Att against four deep learning models: LSTM, combined convolutional neural network and LSTM (CNN-LSTM), ConvLSTM, and ResConvLSTM for spatiotemporal prediction of forest cover in Tasmania, Australia. ResConvLSTM-Att achieved outstanding prediction performance, with an average root mean square error (RMSE) of 6.9% coverage and an impressive average coefficient of determination of 0.965. Compared with LSTM, CNN-LSTM, ConvLSTM, and ResConvLSTM, ResConvLSTM-Att achieved RMSE reductions of 31.2%, 43.0%, 10.1%, and 6.5%, respectively. Additionally, we quantified the impacts of explanatory variables on forest cover dynamics. Our work demonstrated the effectiveness of ResConvLSTM-Att in spatiotemporal data modelling and prediction.

中文翻译：

---

将残差卷积 LSTM 与注意力机制相结合进行时空森林覆盖预测


了解森林覆盖的时空变化对于有效的森林资源管理至关重要。然而，现有模型在同时捕获时间连续性和空间相关性方面通常缺乏准确性。为了应对这一挑战，我们开发了 ResConvLSTM-Att，这是一种集成了残差神经网络、卷积长短期记忆 （ConvLSTM） 网络和注意力机制的新型混合模型。我们针对四种深度学习模型评估了 ResConvLSTM-Att：LSTM、组合卷积神经网络和 LSTM （CNN-LSTM）、ConvLSTM 和 ResConvLSTM，用于澳大利亚塔斯马尼亚州森林覆盖率的时空预测。ResConvLSTM-Att 取得了出色的预测性能，平均均方根误差 （RMSE） 覆盖率为 6.9%，平均决定系数为 0.965，令人印象深刻。与 LSTM、CNN-LSTM、ConvLSTM 和 ResConvLSTM 相比，ResConvLSTM-Att 的 RMSE 降低率分别为 31.2%、43.0%、10.1% 和 6.5%。此外，我们量化了解释变量对森林覆盖动态的影响。我们的工作证明了 ResConvLSTM-Att 在时空数据建模和预测方面的有效性。