Embedded Temporal Convolutional Networks for Essential Climate Variables Forecasting

Sensors

Mahta Moghaddam¹  Grigorios Tsagkatakis²  Maria Myrto Villia²  Panagiotis Tsakalides² 

[1] Department of Electrical Engineering, University of Southern California, Los Angeles, CA 90089, USA;Institute of Computer Science, Foundation for Research and Technology-Hellas (FORTH), 70013 Heraklion, Greece;

关键词: deep learning;    time-series forecasting;    remote sensing;    climate variables;    surface temperature;    soil moisture;   

DOI  :  10.3390/s22051851

来源: DOAJ

【 摘 要 】

Forecasting the values of essential climate variables like land surface temperature and soil moisture can play a paramount role in understanding and predicting the impact of climate change. This work concerns the development of a deep learning model for analyzing and predicting spatial time series, considering both satellite derived and model-based data assimilation processes. To that end, we propose the Embedded Temporal Convolutional Network (E-TCN) architecture, which integrates three different networks, namely an encoder network, a temporal convolutional network, and a decoder network. The model accepts as input satellite or assimilation model derived values, such as land surface temperature and soil moisture, with monthly periodicity, going back more than fifteen years. We use our model and compare its results with the state-of-the-art model for spatiotemporal data, the ConvLSTM model. To quantify performance, we explore different cases of spatial resolution, spatial region extension, number of training examples and prediction windows, among others. The proposed approach achieves better performance in terms of prediction accuracy, while using a smaller number of parameters compared to the ConvLSTM model. Although we focus on two specific environmental variables, the method can be readily applied to other variables of interest.

【 授权许可】

Unknown