Red onion is one of the flagship commodities in the horticultural sector in Indonesia, with Brebes Regency standing out as the country’s largest producing area. However, challenges such as floods and droughts frequently cause crop failures, impacting supply. Additionally, crop failures lead to price surges in several regions, which severely impact underprivileged communities in Indonesia who still rely on imports.

In December 2023, drought affected 930 hectares of red onion fields, while floods in February-March 2024 impacted 547 hectares of land. Consequently, in April 2024, the price of red onions in several regions of Indonesia increased by up to 55.8% compared to the previous month (National Food Agency, 2024). Therefore, an early warning system is crucial to mitigate the risk of climate change on crop yields in vulnerable areas.

To address this issue, we focus on leveraging machine learning to accurately predict the effects of climate change on red onion production in Brebes Regency. By analyzing synoptic data, particularly rainfall and maximum temperature, we trained various machine learning models, including Support Vector Regression (SVR), Neural Network (NN), Recurrent Neural Network (RNN), and Long Short-Term Memory Network (LSTM).

This poster was presented during the APN Early Career Professional Poster and Networking Session, held alongside the APN 26th Joint Intergovernmental and Scientific Planning Group Meetings on 13 June 2024 at the National Research and Innovation Agency (BRIN) in Jakarta, Indonesia.