Detail Abstract

Modeling Lake Surface Water Temperature (LSWT) in Southeast Asia

Abstract

The impact of climate variability/change in Southeast Asian lakes is expected to exacerbate as business-as-usual anthropogenic emissions continue. This posed multiple threats to hundreds of millions of people relying on their ecosystem services. Therefore, it is important to quantify the severity of such impact on these lakes in order to develop a suitable mitigation and adaptation strategy. Lake surface water temperature (LSWT) among many is an important parameter for the physical and biochemical processes occurring within water as well as in air-water interactions because temperature regulates physical, chemical, and biological processes in water. Therefore LSWT is an important indicator to be measured in impact studies, however, this information is often lacking in Southeast Asia region.</br> This study presents preliminary results of LSWT predictive modelling exercise built from ERA5 reanalysis climate data and LSWT from MODIS products using various machine learning and deep learning algorithms. Predictive models have been applied on historical and projected climate data from different GCM-RCMs to predict LSWT time series for the past and future scenarios. Lake-wise trends have been detected and measured. Additionally, evaluation on model performances and accuracy of calculated trends are also provided.