Journal article · 2026 · Open access

Comparative evaluation of statistical, machine learning and deep learning models for multivariate daily rainfall forecasting

Roshini Priya CH, A Meena, Santosha Rathod, B. Balaji Naik

International Journal of Advanced Biochemistry Research, 10(7S), 602–613 · Published 1 July 2026 · DOI 10.33545/26174693.2026.v10.i7sh.9043

Open PDFView at the publisherCite this paper

In brief

“Comparative evaluation of statistical, machine learning and deep learning models for multivariate daily rainfall forecasting” is a 2026 journal article by Roshini Priya CH and 3 co-authors, published in International Journal of Advanced Biochemistry Research. OpenAlex counts 0 citations as of 20 November 2026. It is open access: the full text is free to read at International Journal of Advanced Biochemistry Research.

Citations
0
References
34
Authors
4

Abstract

Aims: To compare statistical, machine learning and deep learning models for multivariate daily rainfall prediction in Dandepalle Mandal, Telangana, India, and assess their usefulness for mandal-level agricultural advisory support. Study Design: Comparative time-series forecasting study using secondary daily weather observations. Place and Duration of Study: Dandepalle Mandal, Mancherial district, Telangana, India, using daily rainfall, maximum temperature and minimum temperature data for 1995-2024. Methodology: Rainfall distribution was examined for zero-rainfall frequency, skewness and kurtosis. Log1p transformation was used to reduce skewness. Machine learning models used lagged rainfall, rolling statistics, calendar indicators and rain/no-rain history features, while neural architectures used sequential rainfall-temperature inputs. ARIMAX, SARIMAX and GARCH variants were used as statistical baselines. Models were evaluated using RMSE, R² and residual diagnostics on the original rainfall scale. Results: The shallow Decision Tree regressor gave the lowest test RMSE (8.7019 mm) with R² = 0.1075, followed by XGBoost (RMSE = 8.8180 mm; R² = 0.0836) and SVR (RMSE = 8.8497 mm; R² = 0.0770). Deep learning models did not outperform the best machine learning models, with RNN and LSTM giving RMSE values of 8.8634 and 8.8868 mm, respectively. Significant Ljung-Box statistics indicated remaining autocorrelation. Conclusion: Parsimonious machine learning models, particularly Decision Tree, XGBoost and SVR, provided the most useful local rainfall prediction results. However, low R² values and residual autocorrelation show that rainfall-temperature inputs alone do not fully capture daily monsoon dynamics.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

CH, R. P., Meena, A., Rathod, S., & Naik, B. B. (2026). Comparative evaluation of statistical, machine learning and deep learning models for multivariate daily rainfall forecasting. International Journal of Advanced Biochemistry Research, 10(7S), 602–613. https://doi.org/10.33545/26174693.2026.v10.i7sh.9043

MLA 9

CH, Roshini Priya, et al. “Comparative evaluation of statistical, machine learning and deep learning models for multivariate daily rainfall forecasting.” International Journal of Advanced Biochemistry Research, vol. 10, no. 7S, 2026, pp. 602–613. https://doi.org/10.33545/26174693.2026.v10.i7sh.9043.

Chicago

CH, Roshini Priya, A Meena, Santosha Rathod, and B. Balaji Naik. 2026. “Comparative evaluation of statistical, machine learning and deep learning models for multivariate daily rainfall forecasting.” International Journal of Advanced Biochemistry Research 10 (7S): 602–613. https://doi.org/10.33545/26174693.2026.v10.i7sh.9043.

Harvard

CH, R. P. et al. (2026) ‘Comparative evaluation of statistical, machine learning and deep learning models for multivariate daily rainfall forecasting’, International Journal of Advanced Biochemistry Research, 10(7S), pp. 602–613. doi:10.33545/26174693.2026.v10.i7sh.9043.

IEEE

R. P. CH, A. Meena, S. Rathod, and B. B. Naik, “Comparative evaluation of statistical, machine learning and deep learning models for multivariate daily rainfall forecasting,” International Journal of Advanced Biochemistry Research, vol. 10, no. 7S, pp. 602–613, 2026, doi: 10.33545/26174693.2026.v10.i7sh.9043.

BibTeX

@article{ch2026comparative,
  title     = {{Comparative evaluation of statistical, machine learning and deep learning models for multivariate daily rainfall forecasting}},
  author    = {CH, Roshini Priya and Meena, A and Rathod, Santosha and Naik, B. Balaji},
  journal   = {International Journal of Advanced Biochemistry Research},
  year      = {2026},
  volume    = {10},
  number    = {7S},
  pages     = {602--613},
  doi       = {10.33545/26174693.2026.v10.i7sh.9043},
  url       = {https://doi.org/10.33545/26174693.2026.v10.i7sh.9043}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI

  • daily rainfall forecasting
  • multivariate time series forecasting
  • XGBoost
  • support vector regression
  • regression trees
  • LSTM
  • recurrent neural networks
  • SARIMAX

Work with this paper

Most-cited papers in Environmental Science

All highly cited Environmental Science papers

Questions about this paper

How do I cite this paper in APA style?

CH, R. P., Meena, A., Rathod, S., & Naik, B. B. (2026). Comparative evaluation of statistical, machine learning and deep learning models for multivariate daily rainfall forecasting. International Journal of Advanced Biochemistry Research, 10(7S), 602–613. https://doi.org/10.33545/26174693.2026.v10.i7sh.9043

How many times has this paper been cited?

0 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at International Journal of Advanced Biochemistry Research: sign in and open the PDF from this page.

Who wrote this paper?

Roshini Priya CH, A Meena, Santosha Rathod, B. Balaji Naik.

What is the DOI of this paper?

10.33545/26174693.2026.v10.i7sh.9043, permanently at https://doi.org/10.33545/26174693.2026.v10.i7sh.9043. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.