EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimizing Crop Yield Forecasts through Deep Neural Network Architectures Using Omdena Dataset

Sweta Singh, Shilpi Shukla, Dr. Yusuf Perwej, Farheen Siddiqui, Dr. Nikhat Akhtar

International Journal of Scientific Research in Science, Engineering and Technology · 25.10.2025 · 12 (5) · 377-389

DOI: 10.32628/ijsrset2513819 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Scientific Research in Science, Engineering and Technology, online erschienen am 25.10.2025. Verfasst von Sweta Singh und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A crop yield forecast is important for making farming more sustainable because it helps farmers use natural resources like water, fertilizers, and soil more efficiently. Farmers and governments can better manage resources when they have accurate yield estimates. This cuts down on waste and protects the environment by preventing problems like soil degradation and water quality issues. Conventional methods for recommending crops often use heuristics or expert knowledge, which may not be accurate or flexible enough to deal with changes in the environment and the market. So, to give farmers the best advice on how to grow crops, we need a data-driven method that uses what we already know about soil, weather, and crops. Early yield prediction models relied on manual calculations, which sometimes contained errors due to potentially inaccurate inputs. To tackle these challenges, this paper introduces an innovative approach by utilizing representative neural network models to assess the accuracy of yield predictions. This paper focuses on the utilization of hybrid and deep learning models, including long short-term memory (LSTM), convolutional neural network (CNN), and recurrent neural network (RNN), to identify the most accurate model and assess yield prediction accuracy. We use the farm production datasets from Omdena to run a number of tests to see how well these algorithms work. These tests help the proposed method figure out how well each model can predict the future, which will help make better predictions about agricultural productivity in the future. These results could greatly improve the accuracy and reliability of yield forecasts, which would be good for the agricultural industry and the economy as a whole.

Zitieren

APA

Singh, S., Shukla, S., Perwej, D. Y., Siddiqui, F., & Akhtar, D. N. (2025). Optimizing Crop Yield Forecasts through Deep Neural Network Architectures Using Omdena Dataset. International Journal of Scientific Research in Science, Engineering and Technology, 12(5), 377-389. https://doi.org/10.32628/ijsrset2513819

Vancouver

Singh S, Shukla S, Perwej DY, Siddiqui F, Akhtar DN. Optimizing Crop Yield Forecasts through Deep Neural Network Architectures Using Omdena Dataset. International Journal of Scientific Research in Science, Engineering and Technology. 2025;12(5):377-389. doi:10.32628/ijsrset2513819

BibTeX
@article{Singh2025,
  author = {Singh, Sweta and Shukla, Shilpi and Perwej, Dr. Yusuf and Siddiqui, Farheen and Akhtar, Dr. Nikhat},
  title = {Optimizing Crop Yield Forecasts through Deep Neural Network Architectures Using Omdena Dataset},
  journal = {International Journal of Scientific Research in Science, Engineering and Technology},
  year = {2025},
  volume = {12},
  number = {5},
  pages = {377--389},
  doi = {10.32628/ijsrset2513819}
}
Kostenlos starten →