The Potential of Deep Learning for Satellite Rainfall Detection over Data-Scarce Regions, the West African Savanna

The Potential of Deep Learning for Satellite Rainfall Detection over Data-Scarce Regions, the West African Savanna

Estebanez Camarena, M. (TU Delft Water Resources)
Taormina, R. (TU Delft Sanitary Engineering)
van de Giesen, N.C. (TU Delft Water Resources)
ten Veldhuis, Marie-claire (TU Delft Water Resources)

2023

Food and economic security in West Africa rely heavily on rainfed agriculture and are threatened by climate change and demographic growth. Accurate rainfall information is therefore crucial to tackling these challenges. Particularly, information about the occurrence and length of droughts as well as the onset date of the rainy season is essential for agricultural planning. However, existing rainfall models fail to accurately represent the highly variable and sparsely monitored West African rainfall patterns. In this paper, we show the potential of deep learning (DL) to model rainfall in the region and propose a methodology to develop DL models in data-scarce areas. We built two DL models for satellite rainfall (rain/no-rain) detection over northern Ghana from Meteosat TIR data based on standard DL architectures: Convolutional neural networks (CNNs) and convolutional long short-term memory neural networks (ConvLSTM). The Integrated Multi-satellitE Retrievals for the Global Precipitation Measurement (GPM) mission (IMERG) and Precipitation Estimation from Remotely Sensed Imagery Using an Artificial Neural Network Cloud Classification System (PERSIANN-CCS) products are used as benchmarks. We use rain gauge data from the Trans-African Hydro-Meteorological Observatory (TAHMO) for model development and performance evaluation. We show that our models compare well against existing products despite being considerably simpler, developed with a small training dataset—i.e., 8 stations covering 2.5 years with 20.4% of the data missing—and using TIR data alone. Concretely, our models consistently outperform PERSIANN-CCS for rain/no-rain detection at a sub-daily timescale. While IMERG is the overall best performer, the DL models perform better in the second half of the rainy season despite their simplicity (i.e., up to 120 k parameters). Our results suggest that DL-based regional models are a promising alternative to state-of-the-art global products for providing regional rainfall information, especially in meteorologically complex regions such as the (sub)tropics, which are poorly covered by ground-based rainfall observations.

deep learning
CNN
ConvLSTM
rainfall detection
satellite rainfall retrieval
West Africa
northern Ghana

http://resolver.tudelft.nl/uuid:9c3bf83f-443d-4666-94e9-d9ef5c86c835

https://doi.org/10.3390/rs15071922

2072-4292

Remote Sensing, 15 (7)

Institutional Repository

journal article

© 2023 M. Estebanez Camarena, R. Taormina, N.C. van de Giesen, Marie-claire ten Veldhuis