Application of deep learning algorithms to correct bias in CMIP6 simulations of surface air temperature over the Indian monsoon core region

Abstract

Indian subcontinent witnessed a rise in surface air temperature (SAT) in recent decades, during the summer months of March, April and May. The monsoon core region (MCR) of India experiences a hot and humid climate, with temperatures typically highest in May and June before the onset of the monsoon. Global climate model (GCM) simulations of SAT are very much essential to understand the future climate of Indian MCR. Biases in GCMs simulations are due to insufficient knowledge of parameterizations and various assumptions that are made to simulate the complex interactions between land, ocean and atmosphere. The objective of this study is to correct the bias in the Coupled Model Intercomparison Project Phase 6 (CMIP6)–GCM simulations of SAT during March, April and May months over MCR for the historical period 1985–2014 and shared socio‐economic pathways (SSPs) SSP2‐4.5 and SSP5‐8.5 for the period 2015–2100. SAT dataset of fifth‐generation reanalysis (ERA5) of the European Centre for Medium‐Range Weather Forecasts (ECMWF) is used as reference dataset to perform bias correction for the historical period. Preliminary investigation of both SAT datasets has shown that there exists considerable warm bias (1.47°C) over the MCR. Bias correction is performed using a one‐dimensional convolutional neural network (CNN‐1D) and a convolutional long short‐term memory network (CNN‐LSTM) deep learning algorithm. The performance of these algorithms is evaluated with the statistical metrics such as root‐mean‐square error (RMSE), normalized root‐mean‐square error, Nash–Sutcliffe efficiency, mean absolute error, percent bias, correlation coefficient and dynamic time warping. RMSE and percent bias were decreased to 0.35°C and 0.8% with CNN‐LSTM algorithm. The CNN‐LSTM algorithm also preserves the year‐to‐year variability of SAT. Hence, CNN‐LSTM algorithm is found to be suitable for the bias correction of GCM simulations of SAT with encouraging results.

Đánh giá sự phù hợp của một số mô hình khí hậu toàn cầu CMIP6-GCMs trong mô phỏng lượng mưa và nhiệt độ trên lưu vực thượng nguồn sông Đồng Nai

“…Trong nghiên này đã sử dụng các chỉ số thống kê sau: (i) Độ lệch phần trăm PBias (Percent Bias), (ii) Độ lệch chuẩn SD (standard deviation), (iii) Sai số bình phương trung bình gốc RMSE (root mean square error), (iv) Hệ số tương quan Pearson (R), và Biểu đồ Taylor để so sánh lượng mưa, nhiệt độ (Tmin, Tmax) trung bình tháng của từng mô hình riêng lẻ với số liệu thực đo tại các trạm quan trắc trong quá khứ. Các chỉ số này thường được áp dụng để đánh giá hiệu xuất mô phỏng các yếu tố lượng mưa và nhiệt độ của các mô hình GCMs [29,30]. Công thức tính của chỉ số thống kê như sau:…”

Statistical downscaling of maximum temperature under CMIP6 global climate models and evaluation of heat wave events using deep learning methods for Indo‐Gangetic Plain

“…The projection of climatic extremes from GCMs datasets show high uncertainty due to different factors like emission scenarios, regional climate variability, model parametrization schemes and internal model physics (Chaubey & Mall, 2023). To mitigate this uncertainty, previous researchers applied different corrections and deep learning methods, which have been found to be efficient at statistical downscaling (Sabarinath et al, 2023;Wang & Tian, 2022). A notable research gap in statistical downscaling lies in the effective integration of advanced machine learning techniques, such as deep learning and ensemble methods, to enhance the accuracy and robustness of downscaling models.…”