Using the coupled machine learning-evolutionary optimization algorithms and climate change projection models to assess the distribution of groundwater-origin aufeis in the North-East of Northern Hemisphere and their dynamic in a changing climate

Abstract

<p>Groundwater-fed aufeis and their dynamic indicate the intensity of water exchange processes in permafrost, including those in a changing climate. Spatiotemporal variation of aufeis has not yet been fully tackled as it entails a holistic understanding of the main hydrological, geological, geomorphological, and climate processes. Meanwhile, robust machine learning (ML) techniques have transcended the ongoing studies by extracting the emerging pattern from a large set of data and predicting future patterns. Once they are coupled with optimization algorithms, they can give even more reliable results by improving their learning capability, known as goodness-of-fit. Hence, the current study sets out to study the spatial pattern of aufeis in the North-East of Northern Hemisphere by adopting a robust pattern recognition algorithms, Support Vector Machine (SVM), coupled with three evolutionary optimization techniques, namely Imperialistic Competitive Algorithm (ICA), Grey Wolf Optimizer (GWO), and Bat optimizer (Bat). The latter was carried out by incorporating a wide range of topo-hydrological, geological, geomorphological, environmental, and climatic data together with the distribution of aufeis as the ground truth in the study region. Adhering to the spatial partitioning method, a different basin with the entire aufeis within was kept apart from the modeling process and used as a reference for model validation. By doing so, the spatial prediction models were sieved through multiple cutoff-dependent and -independent performance metrics to determine the superior model in terms of both learning and prediction/generalization capacity. To assess how the distribution of aufeis responds to different changing conditions, we employed Long Ashton Research Station Weather Generator 6 (LARS-WG6) in CMIP5 protocol under RCP 4.5 and RCP 8.5 scenarios. The model was fed by daily time-series for a suite of climate variables, namely, precipitation, maximum and minimum temperature, and solar radiation, acquired from different synoptic weather stations in the study area. The downscaling performance of the LARS-WG6 model was assessed using the Nash Sutcliffe efficiency metric, bias, and Root Mean Squared Error (RMSE). Further, the climatic variables were projected for the periods 2041&#8211;2060 (2050s) and 2061&#8211;2080 (2070s) using various Atmosphere-Ocean General Circulation Models (AOGCMs), including EC-EARTH, GFDL-CM3, HadGEM2-ES, MIROC5, and MPI-ESM-MR. The projected climatic variables as dynamic drivers were used in combination with the previous static factors as the new set of inputs into the superior hybridized spatial prediction model to investigate the distribution (be it decreasing or increasing pattern) of aufeis across the study area under the considered climate change scenarios. The results revealed that the hybridized SVM-GWO has comparatively higher learning and prediction performance, followed by the other two counterparts, SVM-ICA and SVM-Bat. Based on the applied downscaling performance metrics, the LARS-WG6 and implemented models have proved successful. The projection models results for the two periods in the future attested to an increasing temperature followed by an antithetical pattern for precipitation. The results of SVM-GWO fused to projected climatic variables revealed a transparent pattern based on which the aufeis distribution area will be diminished.&#160;The study is supported by Russian Fund for Basic Research (projects 19-55-80028, 19-35-90090 and 20-05-00666).</p>