Climate-Driven Poverty Prediction in Nusa Tenggara Timur Using Transfer Learning-Based CNN-LSTM and ERA5-Land
Abstract
Poverty dynamics in Nusa Tenggara Timur (NTT), Indonesia, are influenced by climate variability, particularly rainfall deficits and drought, which increase household economic vulnerability. This study develops a transfer learning-based Hybrid CNN-LSTM model to predict the annual poverty headcount ratio (%) across 22 regencies/municipalities in NTT. ERA5-Land monthly total precipitation and annual regency-level poverty data from 2003–2024 were integrated, yielding 484 regency-year observations. To address limited local time-series data, the CNN was pretrained on long-term ERA5-Land climate sequences and transferred to the NTT task, while the LSTM and output layers were fine-tuned using local data. The model achieved R² = 0.87 and outperformed standalone CNN and LSTM models. A 6–12-month lagged association between rainfall deficits and subsequent poverty changes was also identified, suggesting a potential anticipatory climate signal rather than direct causality. The findings highlight the potential of integrating climate reanalysis, transfer learning, and deep learning for poverty-risk prediction in data-constrained regions. However, further operational, institutional, and external validation is required before deployment for decision support.
Related
- Regional climate variability and rice yields prediction in Bangladesh using machine learning and deep learning models
- Physically aligned forest fire risk prediction: A deep learning framework coupling fuel and climate multivariate factors
- Hierarchical Temporal Transformer for Cancer Grade Prediction and Cross-Cancer Transfer Learning from Pathology Reports
- Hierarchical temporal transformer for cancer grade prediction and cross cancer transfer learning from pathology reports
- Layer-Specific Source-Anchored Transfer Learning for Multi-Omics Survival Prediction in Younger Breast Cancer Patients
BibTeX
@article{kaesmetan2026climatedriven,
title = {{Climate-Driven Poverty Prediction in Nusa Tenggara Timur Using Transfer Learning-Based CNN-LSTM and ERA5-Land}},
author = {Yampi R Kaesmetan and Rahmat Gernowo and Budi Warsito},
journal = {Journal of Information Systems and Informatics},
year = {2026},
month = oct,
doi = {10.63158/journalisi.v8i5.1707},
url = {https://doi.org/10.63158/journalisi.v8i5.1707},
note = {CC BY},
}
RIS
TY - JOUR
TI - Climate-Driven Poverty Prediction in Nusa Tenggara Timur Using Transfer Learning-Based CNN-LSTM and ERA5-Land
AU - Yampi R Kaesmetan
AU - Rahmat Gernowo
AU - Budi Warsito
PY - 2026
DA - 2026/10/24
JO - Journal of Information Systems and Informatics
DO - 10.63158/journalisi.v8i5.1707
UR - https://doi.org/10.63158/journalisi.v8i5.1707
AB - Poverty dynamics in Nusa Tenggara Timur (NTT), Indonesia, are influenced by climate variability, particularly rainfall deficits and drought, which increase household economic vulnerability. This study develops a transfer learning-based Hybrid CNN-LSTM model to predict the annual poverty headcount ratio (%) across 22 regencies/municipalities in NTT. ERA5-Land monthly total precipitation and annual regency-level poverty data from 2003–2024 were integrated, yielding 484 regency-year observations. To address limited local time-series data, the CNN was pretrained on long-term ERA5-Land climate sequences and transferred to the NTT task, while the LSTM and output layers were fine-tuned using local data. The model achieved R² = 0.87 and outperformed standalone CNN and LSTM models. A 6–12-month lagged association between rainfall deficits and subsequent poverty changes was also identified, suggesting a potential anticipatory climate signal rather than direct causality. The findings highlight the potential of integrating climate reanalysis, transfer learning, and deep learning for poverty-risk prediction in data-constrained regions. However, further operational, institutional, and external validation is required before deployment for decision support.
SN - 2656-5935
SN - 2656-4882
ER -