The active layer is the top layer of ground subject to the annual thawing and freezing in areas underlain by permafrost. Thermal regime of active layer is a robust indicator of the state of the permafrost system under climate change, which is also one of the key factors in designing, building and maintaining infrastructure in cold regions. Therefore, monitoring the active layer thermal regime is crucial to address some of these engineering concerns. 

However, there is almost little research on the modeling of the interactions between active layer temperature (ALT) and meteorological factors. Besides, few earlier studies have explored the use of wavelet transform and artificial neural network (ANN) hybrid methods to model ALT time series, and compared with the results of ANN model. 

Recently, scientists from the Northwest Institute of Eco-Environment and Resources of Chinese Academy of Sciences discussed the use of ANN and wavelet-ANN (W-ANN) hybrid models to simulate and forecast the ALT time series data based on five weather factors, including air temperature, precipitation, wind speed, downward longwave radiation and downward shortwave radiation. 

They developed ANN-based and W-ANN-based ALT models using various weather factors, which precisely simulated ALT time series data in both warm and cold permafrost zones of the Qinghai-Tibetan Plateau and compared the results of the ANN-based and W-ANN-based ALT models. 

The results demonstrate that ANN and W-ANN models can precisely simulate the ALT. The W-ANN hybrid model that uses decomposed sub-series as input provides forecasting results that are more accurate than the ANN model, which uses original time series. 

This study has been published in the Cold Regions Science and Technology in an article entitled “Simulating active layer temperature based on weather factors on the Qinghai-Tibetan Plateau using ANN and wavelet-ANN models”. 

Contact: 

GAO Siru 

E-mail: gaosiru@lzb.ac.cn 

State Key Laboratory of Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730000, China.