Authors : Dr. Rachana Dhannawat; Smruti Sawant; Ritika Sawant; Shivanshi

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/yc5x4mdy

Scribd : https://tinyurl.com/2wtafwna

DOI : https://doi.org/10.38124/ijisrt/26apr2478

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Agriculture remains central to food security and rural livelihoods, yet farmers continue to face persistent challenges due to environmental variability, fluctuating market conditions, and limited access to data-driven decisionsupport tools. This paper presents AgriSmart, an integrated AI-driven framework designed to support modern farming through three key functional modules: crop harvest optimization, intelligent crop recommendation, and flood risk early warning. The harvest optimization module utilizes hybrid machine learning models to forecast optimal harvest timing using agricultural market data from Pune spanning 2020–2025. The dataset includes price information for 22 crops: onion, potato, rice, maize, wheat, black gram (whole), cabbage, grapes, cauliflower, watermelon, orange, papaya, beetroot, garlic, carrot, spinach, green peas, brinjal, bottle gourd, ridge gourd, and tomato.The crop recommendation module evaluates multiple machine learning classifiers, including Random Forest, XGBoost, CatBoost, Support Vector Machine (SVM), and Gaussian Naive Bayes, to recommend suitable crops based on soil and environmental attributes. The Early Flood Alert Module operates as a Multi-Class Classification System using an XGBoost algorithm able to process multiple variables rainfall, humidity, soil type, terrain slope and crop growth stage to predict the risk of waterlogging for a farmer and generate advance notice of this risk to the farmer.

Keywords : Artificial Intelligence, Crop Harvest Optimization, Crop Recommendation, Flood Risk Prediction, Machine Learning, Sustainable Agriculture, Precision Agriculture, XGBoost, Random Forest, Land Suitability Rating.

References :

1. S. C. Liu et al., “A crop harvest time prediction model for better sustainability integrating feature selection and artificial intelligence methods,” Sustainability, vol. 14, no. 21, Art. no. 14101, 2022.
2. N. P. Sable, V. K. Shukla, P. N. Mahalle, and V. Khedkar, “Optimizing agricultural yield: A predictive model for profitable crop harvesting based on market dynamics,” Frontiers in Computer Science, vol. 7, Art. no. 1567333, 2025, doi: 10.3389/fcomp.2025.1567333.
3. B. Dey, J. Ferdous, and R. Ahmed, “Machine learning based recommendation of agricultural and horticultural crop cultivation,” Heliyon, vol. 10, no. 3, Art. no. e25112, 2024, doi: 10.1016/j.heliyon.2024.e25112.
4. R. Costache et al., “Flash-flood susceptibility assessment using multicriteria decision making and machine learning supported by remote sensing and GIS techniques,” Environ. Model. Softw., vol. 160, Art. no. 105583, 2023, doi: 10.1016/j.envsoft.2022.105583.
5. Z. Wang et al., “Flood susceptibility mapping using ensemble machine learning models based on a novel PCA-weighting method,” Sci. Total Environ., vol. 886, Art. no. 163925, 2023, doi: 10.1016/j.scitotenv.2023.163925.
6. A.                Ingle,      “Crop     recommendation  dataset,” Kaggle,  Dec.        2020.
7. [Online]. Available: https://www.kaggle.com/datasets/atharvaingle/croprecommendation-dataset
8. A.F. Jadama, B. Jobarteh, M. M. Islam, and M. K. Toray, “Ensemble learning: Methods, techniques, application,” University of New Brunswick, Fredericton, NB, Canada, 2024. doi:
9. 10.13140/RG.2.2.28017.08802.
10. M. K. Senapaty, A. Ray, and N. Padhy, “A decision support system for crop recommendation using machine learning classification algorithms,” Agriculture, vol. 14, no. 8, Art. no. 1256, 2024, doi: 10.3390/agriculture14081256.
11. S. Pariselvam, C. Loganath, M. Kiran Kumar, and M. Aravind, “AI based crop recommendation and finding the profitable region to sell the crop,” African Journal of Biomedical Research, vol. 27, no. 4S, pp. 15109– 15114, 2024, doi: 10.53555/AJBR.v27i4S.7565.
12. A.Khan, S. Shahid, H. Ahmed, T. Ismail, N. Nawaz, and M. Wang, “Machine learning-based flood prediction techniques: A comprehensive review,” Environmental Modelling & Software, vol. 143, Art. no. 105284, 2021, doi: 10.1016/j.envsoft.2021.105284.
13. Y. Zhang, X. Liu, and H. Chen, “A comprehensive review of machine learning approaches for flood depth estimation,” International Journal of Disaster Risk Science, vol. 16, pp. 433–445, 2025, doi: 10.1007/s13753025-00639-0.
14. O. Turgut, I. Kok, and S. Ozdemir, “AgroXAI: Explainable AI-driven crop recommendation system for agriculture 4.0,” arXiv:2412.16196, 2024.