Performance Evaluation of Machine Learning Models for Standardized Precipitation Index Prediction in Pandeglang

Indri  Hapsari

doi:10.52436/1.jutif.2026.7.4.5566

Authors

Indri Hapsari Meteorological Center Climatology and Geophysics Region II, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.4.5566

Keywords:

Drought Prediction, Machine Learning, Pandeglang, Standardized Precipitation Index

Abstract

Drought is a significant climate change-driven extreme event that severely impacts agriculture and water resource management, particularly in regions like Pandeglang, Banten, which is vital for food security. This study aims to evaluate and compare the performance of four machine learning algorithms—Multiple Linear Regression (MLR), Artificial Neural Networks (ANN), K-Nearest Neighbors (KNN), and XGBoost (XGB)—in predicting the Standardized Precipitation Index (SPI) across short, medium, and long-term timescales (3, 6, 9, and 12 months). The methodology involves utilizing historical daily rainfall data (1991–2024) and executing a multi-scale comparative analysis using six different lag times within a Python-based framework. Performance was measured using RMSE, MAE, NSE, and R² metrics. The results demonstrate that predictive accuracy consistently improves as the SPI timescale increases, with the 12-month scale (SPI-12) offering the most stable results. The ANN model was the most reliable algorithm, with a peak R² of 0.961 at the 12-month scale. Conversely, the XGB model showed the poorest performance on shorter scales when historical data was limited. This research provides a localized, computationally efficient framework for informatics-based climate monitoring. By establishing optimal lag windows and model complexity requirements, it bridges the gap between algorithmic theory and practical application for developing data-driven early warning systems.

Downloads

Download data is not yet available.

References

M. Niazkar, R. Piraei, G. E. Türkkan, T. Hırca, F. Gangi, and S. H. Afzali, “Drought Analysis using Innovative Trend Analysis and Machine Learning Models for Eastern Black Sea Basin,” Theoretical and Applied Climatology, vol. 155, no. 10, pp. 1605–1624, 2023, doi: 10.1007/s00704-023-04710-y.

R. Piraei, M. Niazkar, F. Gangi, and G. E. Türkkan, “Short-Term Drought Forecast across Two Different Climates,” Hydrology, vol. 11, no. 10, pp. 1–18, 2024, doi: 10.3390/hydrology11100163.

D. A. Wilhite and M. Lantz, “Understanding the Drought Phenomenon: The Role of Definitions.pdf,” Water International, vol. 10, no. 3, pp. 111–120, 1985, doi: 10.1080/02508068508686328.

I. Tanriverdi and İ. Batmaz, “AI‑driven U.S. Drought Prediction using Machine Learning and Deep Learning,” Climate Dynamics, vol. 63, no. 249, pp. 1–24, 2025, doi: 10.1007/s00382-025-07720-w.

S. Lee, Ji-Wan; Hong, Eun-Mi; Jang, Won-Jin; Kim, “Assessment of Socio-economic Drought Information using Drought-related Internet News Data (Part A: Socio-economic Drought Data Construct and Evaluation Socio-economic Drought Information),” International Journal of Disaster Risk Reduction, vol. 75, no. 6, 2022, doi: 10.1016/j.ijdrr.2022.102961.

S. Eslamian, K. Ostad-ali-askari, V. P. Singh, and N. R. Dalezios, “A Review of Drought Indices,” International Journal of Constructive Research in Civil Engineering, vol. 3, no. 4, pp. 48–66, 2017, doi: 10.20431/2454-8693.0304005.

B. Poudel, D. Dahal, M. Banjara, and A. Kalra, “Assessing Meteorological Drought Patterns and Forecasting Accuracy with SPI and SPEI Using Machine Learning Models,” Forecasting, vol. 6, no. 11, pp. 1026–1044, 2024, doi: 10.3390/forecast6040051.

T. B. McKee, N. J. Doesken, and J. Kleist, “The Relationship of Drought Frequency and Duration to Time Scales,” in Eighth Conference on Applied Climatology, 1993, pp. 17–22.

T. Barış and T. Bihrat, “Drought Analysis Based on Nonparametric Multivariate Standardized Drought Index in the Seyhan River Basin,” Natural Hazards, vol. 121, no. 9, pp. 11051–11078, 2025, doi: 10.1007/s11069-025-07234-y.

M. N. Lorenzo, H. Pereira, I. Alvarez, and J. M. Dias, “Standardized Precipitation Index (SPI) Evolution Over the Iberian Peninsula During the 21st Century,” Atmospheric Research, vol. 297, no. 2, pp. 1–19, 2024, doi: 10.1016/j.atmosres.2023.107132.

M. Lotfirad, H. E. Gisavandani, and A. Arash, “Drought Monitoring and Prediction using SPI, SPEI, and Random Forest Model in Various Climates of Iran,” Journal of Water and Climate Change, vol. 13, no. 2, pp. 383–406, 2022, doi: 10.2166/wcc.2021.287.

H. Citakoglu and Ö. Coşkun, “Comparison of Hybrid Machine Learning Methods for the Prediction of Short‑term Meteorological Droughts of Sakarya Meteorological Station in Turkey,” Environmental Science and Pollution Research, vol. 29, no. 50, pp. 75487–75511, 2022, doi: 10.1007/s11356-022-21083-3.

Mislan, Haviluddin, S. Hardwinarto, Sumaryono, and M. Aipassa, “Rainfall Monthly Prediction Based on Artificial Neural Network: A Case Study in Tenggarong Station, East Kalimantan - Indonesia,” in Procedia Computer Science, Elsevier Masson SAS, 2015, pp. 142–151. doi: 10.1016/j.procs.2015.07.528.

O. Kandasamy, N. Maragatham, S. Eagan, R. R., B. Kannan, and P. C., “Rainfall Prediction using Artificial Neural Networks and Machine Learning Algorithms over the Coimbatore Region,” Journal of Water and Climate Change, vol. 16, no. 3, pp. 946–959, 2025, doi: 10.2166/wcc.2025.576.

A. Raja and T. Gopikrishnan, “Drought Prediction and Validation for Desert Region using Machine Learning Methods,” International Journal of Advanced Computer Science and Applications, vol. 13, no. 7, pp. 47–53, 2022, doi: 10.14569/IJACSA.2022.0130707.

K. En-nagre, M. Aqnouy, A. Ouarka, A. S. Naqvi, I. Bouizrou, J. E. S. El Messari, et al., “Climate Risk Management Assessment and Prediction of Meteorological Drought using Machine Learning Algorithms and Climate Data,” Climate Risk Management, vol. 45, no. 6, pp. 1–20, 2024, doi: 10.1016/j.crm.2024.100630.

M. S. Oyounalsoud, A. G. Yilmaz, M. Abdallah, and A. Abdeljaber, “Drought Prediction using Artificial Intelligence Models based on Climate Data and Soil Moisture,” Scientific Reports, vol. 14, no. 8, pp. 1–16, 2024, doi: 10.1038/s41598-024-70406-6.

D. H. Ha, P. N. Duc, T. H. Luong, T. T. Duc, T. T. Ngoc, T. N. Minh, et al., “Applied Sciences Application of Artificial Intelligence to Forecast Drought Index for the Mekong Delta,” Applied Sciences, vol. 14, no. 8, pp. 1–30, 2024, doi: 10.3390/app14156763.

S. W. Kim, D. Jung, and Y.-J. Choung, “Development of a Multiple Linear Regression Model for Meteorological Drought Index Estimation Based on Landsat Satellite Imagery,” Water, vol. 12, no. 12, pp. 1–16, 2020, doi: 10.3390/w12123393.

M. Li, Y. Yao, Z. Feng, and M. Ou, “Hydrological Drought Prediction and Its Influencing Features Analysis Based on a Machine Learning Model,” Natural Hazards and Earth System Sciences, vol. 25, no. 11, pp. 4299–4316, 2025, doi: 10.5194/nhess-25-4299-2025.

S. Park and H. Han, “Application of LSTM and Climate Index for Prediction of Meteorological Drought in South Korea,” Water, vol. 17, no. 12, pp. 1–15, 2025, doi: 10.3390/w17121801.

A. Jierula, S. Wang, T. Oh, and P. Wang, “Applied Sciences Study on Accuracy Metrics for Evaluating the Predictions of Damage Locations in Deep Piles Using Artificial Neural Networks with Acoustic Emission Data,” Applied Sciences, vol. 11, no. 3, pp. 1–20, 2021, doi: 10.3390/app11052314.

S. Sharma and S. Kumari, “Comparison of Machine Learning Models for Flood Forecasting in the Mahanadi River Basin, India,” Water and Climate Change, vol. 15, no. 4, pp. 1629–1652, 2024, doi: 10.2166/wcc.2024.517.

D. Desmawan, E. Halwatunnisa, M. R. Syahputra, Sania, B. Pratiwi, S. Humairoh, et al., “Peran Pemerintah dalam Mewujudkan Ketahanan Pangan Bidang Pertanian di Kabupaten Pandeglang,” Jurnal Perubahan Ekonomi, vol. 8, no. 12, pp. 273–278, 2024, [Online]. Available: https://oaj.jurnalhst.com/index.php/jpe/article/view/7397/8373

A. Sjafari and K. S. Nugroho, “Strategi Daerah Pembangunan Daerah Tertinggal Kabupaten Pandeglang Tahun 2017-2021,” Pandeglang District, 2018. [Online]. Available: https://www.researchgate.net/publication/372646669_B2_STRADA_Pandeglang

Ministry of Agriculture, “Panen Raya di Pandeglang, Kebijakan Tanam 1 Juta Hektar Sudah Tepat.” Accessed: Jan. 15, 2026. [Online]. Available: https://www.pertanian.go.id/home/?show=news&act=view&id=2471

Central Bureau of Statistics, “Distribusi Persentase Produk Domestik Regional Bruto Atas Dasar Harga Berlaku Menurut Lapangan Usaha (persen) di Kabupaten Pandeglang, 2024.” Accessed: Jan. 15, 2026. [Online]. Available: https://pandeglangkab.bps.go.id/id/statistics-table/3/T0UxS09GQlBTbk5QWTBNdlVWUmxSMjV3Y3l0VWR6MDkjMw==/distribusi-persentase-produk-domestik-regional-bruto-atas-dasar-harga-berlaku-menurut-lapangan-usaha--persen--di-kabupaten-pandeglang--2022.html?year=20

F. Safira, “Agricultural Drought and Rice Productivity in Pandeglang Regency,” University of Indonesia, 2020.

iNews, “Dampak Kemarau, Petani di Pandeglang Rugi Puluhan Juta Akibat Gagal Panen.” Accessed: Jan. 15, 2026. [Online]. Available: https://pandeglang.inews.id/read/484850/dampak-kemarau-petani-di-pandeglang-rugi-puluhan-juta-akibat-gagal-panen

National Agency for Disaster Countermeasure, “Kajian Risiko Bencana Provinsi Banten 2022-2026.” Accessed: Jan. 15, 2026. [Online]. Available: https://inarisk.bnpb.go.id/pdf/Banten/Dokumen KRB Prov. Banten_final draft.pdf

J. Mallick, S. Talukdar, M. Alsubih, R. Salam, M. Ahmed, N. Ben Kahla, et al., “Analysing the Trend of Rainfall in Asir Region of Saudi Arabia using the Family of Mann-Kendall Tests, Innovative Trend Analysis, and Detrended Fluctuation Analysis,” Theoretical and Applied Climatology, vol. 143, no. 11, pp. 823–841, 2020, doi: 10.1007/s00704-020-03448-1.

C. Zhao and J. Yang, “A Robust Skewed Boxplot for Detecting Outliers in Rainfall Observations in Real-Time Flood Forecasting,” Advances in Meteorology, vol. 2019, no. 2, pp. 1–8, 2019, doi: 10.1155/2019/1795673.

H. N. Irmanda, Ermatita, M. K. Awang, and M. Adrezo, “Enhancing Weather Prediction Models through the Application of Random Forest Method and Chi-Square Feature Selection,” International Journal on Informatics Visualization, vol. 8, no. 3–2, pp. 1506–1514, 2024, doi: 10.62527/joiv.8.3.2356.

M. Ehteram and F. B. Banadkooki, “A Developed Multiple Linear Regression (MLR) Model for Monthly Groundwater Level Prediction,” Water, vol. 15, no. 22, p. 3940, 2023, doi: 10.3390/w15223940.

S. Haykin, Neural Networks: A Comprehensive Foundation, Second Edi. Pearson Education, 1999.

L. Zhang, F. Zhang, W. Du, M. Hu, Y. Hao, S. Ding, et al., “Machine Learning Analysis of Maize Seedling Traits Under Drought Stress,” Biology, vol. 14, no. 7, pp. 1–20, 2025, doi: 10.3390/biology14070787.

V. Luong and H. Bui, “Evaluation of Models and Drought-wetness Factors Contributing to Predicting the Vegetation Health Index in Dak Nong Province, Vietnam,” Environmental Research Communications, vol. 6, no. 4, pp. 1–16, 2024, doi: 10.1088/2515-7620/ad39a4.