Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{196212,
        author = {Tanvi Markad and Pooja Ladhawe and Gayatri Deshmukh and Ayush Gavhane and Neha Chede},
        title = {Forecasting Crop Yield Depending on Weather Patterns in Vidarbha using Statistics and Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {4097-4102},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196212},
        abstract = {Agriculture is the primary source of income for the majority population of the Vidarbha region of Maharashtra. The crops cultivated in the region depend heavily on rainfall, and due to unpredictable monsoon pattern and droughts the crop production of the region is highly uncertain and thus leading to a large agrarian crisis in the region. The conventional crop yield estimation techniques based on averaging historic yields or performing linear regression models does not take in account of factors contributing in a more holistic manner. In this research paper, we have designed and developed a hybrid framework for weather-based crop yield prediction using statistical analysis and machine learning. The model takes in inputs meteorological parameters such as temperature, rainfall, humidity and wind speed and other soil parameters like pH, soil moisture and soil nutrients of a plot to predict the yield of key crops of Vidarbha such as soybean, cotton and wheat. Various machine learning techniques such as Random Forest Regressor and gradient boosting machines are applied to model the complex relationship between yield and influencing parameters. These models are able to learn complex non-linear relationships which help in improving accuracy of the predictions. A Flask web application along with an API based on machine learning approach is implemented. The input required is current weather data from OpenWeatherMap and imagery from NASA EPIC API for identifying various crop related risks. The experimental results for Random Forest Regressor have obtained an R score of 0.89 and an RMSE value of 0.34 tons/hectare and performed better than linear regression. It also includes soil analysis, irrigation requirement, pest prediction to help farmers to take informed decisions.},
        keywords = {Crop Yield Forecasting, Weather Prediction, Statistical Analysis, Machine Learning, Random Forest, Vidarbha Agriculture, Flask Web Application, Sustainable Farming},
        month = {April},
        }