EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integrating Crop Types, Yield Products, and Price Forecasting with Explainable AI for Agricultural APIs

Ohnmar Khin, Sungkeun Lee

Crops · 14.07.2026 · 6 (4) · 67

DOI: 10.3390/crops6040067 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Crops, online erschienen am 14.07.2026. Verfasst von Ohnmar Khin und 1 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea government.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The economies of developing countries are mostly dependent on agriculture, with farming serving as many people’s primary source of income. This research aims to enhance agricultural productivity in three primary areas: crop recommendation, yield prediction, and price forecasting. The study uses remote sensing data and five different datasets to assess prediction in agribusiness. The performance strength is then assessed using statistical analysis and model parameters. The next step is to compare the results with earlier traditional machine learning techniques. Three main approaches are used in this study. (1) Hybrid technique for yield prediction: This method employs the Gradient Boosting Regressor, CatBoost Regressor, and Bagging Regressor to predict agricultural yield utilising the ensemble aggregation technique of stacking. (2) Yeo–Johnson transformer and multinomial logistic regression: A combination model is used to recommend appropriate crop varieties based on remote sensing data to improve precision agriculture. (3) deep Neural Network-based Price Forecasting: The study used deep neural network models, namely a Multi-Layer Perceptron (MLP), a novel application, to predict future crop market prices. The next stage uses real-time LIME deployment to produce fast forecasts. Lastly, there is a correlation between farm integration and workflow, business effect, and performance. This forecast study’s ultimate goal is to provide farmers with thorough crop prediction to meet the growing demand in the agricultural sector. By combining crop selection, production estimation, and market analysis into a single integrated system, the entire framework seeks to enable well-informed agricultural planning. We plan to develop a mobile application in the future that will provide users with access to a multitude of data, making it easier to anticipate different crops for the agricultural market at all times.

Förderung

  • Korea government

Zitieren

APA

Khin, O., & Lee, S. (2026). Integrating Crop Types, Yield Products, and Price Forecasting with Explainable AI for Agricultural APIs. Crops, 6(4), 67. https://doi.org/10.3390/crops6040067

Vancouver

Khin O, Lee S. Integrating Crop Types, Yield Products, and Price Forecasting with Explainable AI for Agricultural APIs. Crops. 2026;6(4):67. doi:10.3390/crops6040067

BibTeX
@article{Khin2026,
  author = {Khin, Ohnmar and Lee, Sungkeun},
  title = {Integrating Crop Types, Yield Products, and Price Forecasting with Explainable AI for Agricultural APIs},
  journal = {Crops},
  year = {2026},
  volume = {6},
  number = {4},
  pages = {67},
  doi = {10.3390/crops6040067}
}
Kostenlos starten →