Satellite-based extreme precipitation estimation using convolution neural networks and ant colony optimized multi-layers perceptron

Extreme precipitation events have recently increased due to global warming, leading to higher humidity and temperatures. Therefore, accurate, updated, and comprehensive precipitation estimations are essential to mitigate the severe losses caused by these extreme events. Satellite precipitation products provide high spatiotemporal resolution and global coverage, enabling improved detection and estimation of precipitation, especially in areas with limited ground observations. This research leverages some of the advanced satellite precipitation products and atmospheric dataset reanalysis available, enhancing the accuracy of precipitation estimates, particularly during heavy and extreme precipitation events. In this work, we use Convolutional Neural Networks (CNN) and optimization techniques to introduce a two-step methodology for improving satellite-based estimation and detection of heavy and extreme precipitation events. In the first step, feature centroids are integrated into a resampling method to increase the diversity of samples. The second step applies the Ant Colony Optimization (ACO) algorithm to refine categorical evaluation criteria, enhancing prediction accuracy. This study uses the ACO meta-heuristic algorithm to optimize a Multi-Layer Perceptron (MLP) model, using CNN-based precipitation estimates as input. The performance of the models and products in estimating and detecting heavy and extreme precipitation events is evaluated using various metrics, including Pearson correlation (r) and Kling-Gupta Efficiency (KGE). The results show that the Ant Colony-optimized MLP (ACO-MLP) outperforms the satellite precipitation products and CNN models in estimating the extreme and heavy precipitation with r = 0.89, 0.82, and KGE = 0.71, 0.65, over the continental area of Australia. The result of utilizing the proposed ACO-MLP and CNN models in Australia showed that the spatial pattern of the extreme precipitation event over the country's east coast on 23 February 2022 is effectively captured. This work contributes to improving water resources management and advancing climate studies, particularly in understanding and addressing extreme precipitation conditions. • Convolutional Neural Networks (CNN) examined by Centroid features of the input data using an n × n filter in detecting and estimating of heavy and Extreme precipitation Events. • The Ant Colony Meta heuristic algorithm is used to optimize a Multi-Layer Perceptron (ACO-MLP) with the input of the CNN model and a complex Loss function to improve the estimates of heavy and extreme precipitation. • The Proposed Model effectively captures severe precipitation events, especially over vulnerable areas. • The ACO-MLP model outperforms the other models and precipitation products during an extreme precipitation event on 23 February 2022 over the east coast of Australia.