A Review of End-to-End Precipitation Prediction Using Remote Sensing Data: from Divination to Machine Learning

TL;DR

This review surveys the historical and technical trajectory of end-to-end precipitation prediction using remote sensing, tracing from ancient observational practices to modern ML-driven pipelines. It organizes knowledge around key datasets (ERA5, SEAS5, GOES, PRISM, IMERG, SEVIR) and model families (ANNs, CNNs, RNNs/LSTMs, GNNs, GANs, Transformers), highlighting how end-to-end learning leverages raw observations and multimodal data. The authors identify major advances, including physics-informed hybrids and transformer-based nowcasting, while outlining critical challenges in generalization, extreme-events, interpretability, and operational feasibility. They propose future directions focused on region-agnostic transfer learning, extreme-event optimization, multi-modal integration, scalable architectures, and rigorous benchmarking to advance practical, reliable precipitation forecasting.

Abstract

Precipitation prediction has undergone a profound transformation -- from early symbolic and empirical methods rooted in divination and observation, to modern technologies based on atmospheric physics and artificial intelligence. This review traces the historical and technological evolution of precipitation forecasting, presenting a survey about end-to-end precipitation prediction technologies that spans ancient practices, the foundations of meteorological science, the rise of numerical weather prediction (NWP), and the emergence of machine learning (ML) and deep learning (DL) models. We first explore traditional and indigenous forecasting methods, then describe the development of physical modeling and statistical frameworks that underpin contemporary operational forecasting. Particular emphasis is placed on recent advances in neural network-based approaches, including automated deep learning, interpretability-driven design, and hybrid physical-data models. By compositing research across multiple eras and paradigms, this review not only depicts the history of end-to-end precipitation prediction but also outlines future directions in next generation forecasting systems.

Figures (8)

• Figure 1: E2E prediction models in atmospheric application. a) Statistical mode. b) Machine learning model.
• Figure 2: ANN Model by Chen et al.TaoChen1993.
• Figure 3: PERSIANN Model by Hsu et al.Hsu1997.
• Figure 4: Convolution and Max Pooling.
• Figure 5: PERSIANN-CNN Model by Sadeghi et al.Mojtaba2019.