Conference paper · 2026 · Open access

AI-Driven PSO-Optimized Hybrid Framework for Sustainable Rainfall Prediction to Support Agricultural Planning in Monsoonal Regions: A Case Study of Hyderabad

International Conference on Biological Research and Applied Science (ICBRAS) · Published 20 January 2026 · DOI 10.37962/ibras_2026_32-33

Open PDFCite this paper

In brief

“AI-Driven PSO-Optimized Hybrid Framework for Sustainable Rainfall Prediction to Support Agricultural Planning in Monsoonal Regions: A Case Study of Hyderabad” is a 2026 conference paper, published in International Conference on Biological Research and Applied Science (ICBRAS). OpenAlex counts 0 citations as of 20 November 2026. It is open access: the full text is free to read at International Conference on Biological Research and Applied Science (ICBRAS).

Citations
0
References
5

Abstract

In Pakistan's monsoonal regions, accurate short-term precipitation forecasting is essential for climateresilient decision-making, environmental sustainability, and agricultural biotechnology.Irrigation scheduling, crop disease prevention, fertilizer planning, and flood-aware agriculture management are all directly impacted by rainfall uncertainty.For reliable day-ahead rainfall categorization in Hyderabad, Sindh, this study suggests an AI-enabled, big-data-driven hybrid computing architecture optimized by Particle Swarm Optimization (PSO).A rich environmental dataset pertinent to sustainable climate-smart agriculture is represented by the framework's 20 heterogeneous meteorological predictors, which include temperature, humidity, wind dynamics, barometric pressure, IMERG satellite rainfall, and radiation/UV indices.The model uses a nested 5×5 TimeSeriesSplit with a 14-day temporal embargo to guarantee accurate forecasting and avoid temporal leakage, allowing for rigorous chronological examination.To lessen class imbalance without tainting test data, data preprocessing techniques include uniform scaling, mutual-information-based feature selection, and the selective use of SMOTE exclusively on training folds.Two hybrid ensembles a KNN+LR model and a PSO-optimized hybrid system-are added to the baseline classifiers (Random Forest, K-Nearest Neighbors, Logistic Regression, and Support Vector Classifier).Adaptive learning from intricate monsoonal climate patterns is made possible by PSO's joint optimization of soft-voting ensemble weights, the LR regularization parameter (C), and the KNN neighborhood size (k).Over ten temporally ordered evaluation runs (2 seeds × 5 folds), the PSO-optimized hybrid continuously outperforms all baseline approaches, obtaining ACC = 0.859, F1 = 0.869, ROC-AUC = 0.936, and PR-AUC = 0.947.This work presents a useful early-warning rainfall prediction system that helps sustainable agricultural planning and environmental monitoring in monsoonal cities like Hyderabad by combining intelligent optimization, hybrid learning, and rigorous time-aware evaluation.

Cite this paper

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

APA 7

AI-Driven PSO-Optimized Hybrid Framework for Sustainable Rainfall Prediction to Support Agricultural Planning in Monsoonal Regions: A Case Study of Hyderabad. (2026). International Conference on Biological Research and Applied Science (ICBRAS). https://doi.org/10.37962/ibras_2026_32-33

MLA 9

“AI-Driven PSO-Optimized Hybrid Framework for Sustainable Rainfall Prediction to Support Agricultural Planning in Monsoonal Regions: A Case Study of Hyderabad.” International Conference on Biological Research and Applied Science (ICBRAS), 2026. https://doi.org/10.37962/ibras_2026_32-33.

Chicago

2026. “AI-Driven PSO-Optimized Hybrid Framework for Sustainable Rainfall Prediction to Support Agricultural Planning in Monsoonal Regions: A Case Study of Hyderabad.” International Conference on Biological Research and Applied Science (ICBRAS). https://doi.org/10.37962/ibras_2026_32-33.

Harvard

(2026) ‘AI-Driven PSO-Optimized Hybrid Framework for Sustainable Rainfall Prediction to Support Agricultural Planning in Monsoonal Regions: A Case Study of Hyderabad’, International Conference on Biological Research and Applied Science (ICBRAS). doi:10.37962/ibras_2026_32-33.

IEEE

“AI-Driven PSO-Optimized Hybrid Framework for Sustainable Rainfall Prediction to Support Agricultural Planning in Monsoonal Regions: A Case Study of Hyderabad,” International Conference on Biological Research and Applied Science (ICBRAS), 2026, doi: 10.37962/ibras_2026_32-33.

BibTeX

@inproceedings{anon2026driven,
  title     = {{AI-Driven PSO-Optimized Hybrid Framework for Sustainable Rainfall Prediction to Support Agricultural Planning in Monsoonal Regions: A Case Study of Hyderabad}},
  booktitle = {International Conference on Biological Research and Applied Science (ICBRAS)},
  year      = {2026},
  doi       = {10.37962/ibras_2026_32-33},
  url       = {https://doi.org/10.37962/ibras_2026_32-33}
}

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

  • precipitation forecasting
  • monsoon
  • particle swarm optimization
  • hybrid ensemble model
  • soft voting
  • short-term precipitation forecasting
  • climate-smart agriculture
  • irrigation scheduling

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?

AI-Driven PSO-Optimized Hybrid Framework for Sustainable Rainfall Prediction to Support Agricultural Planning in Monsoonal Regions: A Case Study of Hyderabad. (2026). International Conference on Biological Research and Applied Science (ICBRAS). https://doi.org/10.37962/ibras_2026_32-33

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 Conference on Biological Research and Applied Science (ICBRAS): sign in and open the PDF from this page.

What is the DOI of this paper?

10.37962/ibras_2026_32-33, permanently at https://doi.org/10.37962/ibras_2026_32-33. 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.