Summary of Corn Yield Prediction Model with Deep Neural Networks For Smallholder Farmer Decision Support System, by Chollette C. Olisah et al.
Corn Yield Prediction Model with Deep Neural Networks for Smallholder Farmer Decision Support System
by Chollette C. Olisah, Lyndon Smith, Melvyn Smith, Morolake O. Lawrence, Osita Ojukwu
First submitted to arxiv on: 8 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach to crop yield prediction by modeling the interaction between weather and soil variables using deep learning techniques. The authors argue that traditional models have overlooked this interaction, leading to inaccurate predictions. They design a deep neural network regressor (DNNR) with careful consideration of its architecture and hyperparameters. Additionally, they introduce a new metric, average of absolute root squared error (ARSE), which combines the strengths of root mean square error (RMSE) and mean absolute error (MAE). The proposed models, including DNNR, optimised random forest regressor (RFR), and extreme gradient boosting regressor (XGBR), demonstrate impressive performance in predicting crop yields. However, the authors highlight that the best-performing model is one that generalizes well to unforeseen data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Crop yield prediction has been a challenge for farmers, with many models failing to account for important interactions between weather and soil variables. This paper proposes a new approach using deep learning techniques to improve predictions. The authors design a special kind of neural network called a deep neural network regressor (DNNR) that takes these interactions into account. They also introduce a new way to measure how well the model does, which combines two other popular methods. The results show that their models are very good at predicting crop yields, but the best one is the one that can be used in real-life situations. |
Keywords
* Artificial intelligence * Deep learning * Extreme gradient boosting * Mae * Neural network * Random forest
