Hasan Mahmudul, Marjan Md Abu, Uddin Md Palash, Afjal Masud Ibn, Kardy Seifedine, Ma Shaoqi, Nam Yunyoung
Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur, Bangladesh.
School of Information Technology, Deakin University, Geelong, VIC, Australia.
Front Plant Sci. 2023 Aug 10;14:1234555. doi: 10.3389/fpls.2023.1234555. eCollection 2023.
Agriculture is the most critical sector for food supply on the earth, and it is also responsible for supplying raw materials for other industrial productions. Currently, the growth in agricultural production is not sufficient to keep up with the growing population, which may result in a food shortfall for the world's inhabitants. As a result, increasing food production is crucial for developing nations with limited land and resources. It is essential to select a suitable crop for a specific region to increase its production rate. Effective crop production forecasting in that area based on historical data, including environmental and cultivation areas, and crop production amount, is required. However, the data for such forecasting are not publicly available. As such, in this paper, we take a case study of a developing country, Bangladesh, whose economy relies on agriculture. We first gather and preprocess the data from the relevant research institutions of Bangladesh and then propose an ensemble machine learning approach, called K-nearest Neighbor Random Forest Ridge Regression (KRR), to effectively predict the production of the major crops (three different kinds of rice, potato, and wheat). KRR is designed after investigating five existing traditional machine learning (Support Vector Regression, Naïve Bayes, and Ridge Regression) and ensemble learning (Random Forest and CatBoost) algorithms. We consider four classical evaluation metrics, i.e., mean absolute error, mean square error (MSE), root MSE, and , to evaluate the performance of the proposed KRR over the other machine learning models. It shows 0.009 MSE, 99% for Aus; 0.92 MSE, 90% for Aman; 0.246 MSE, 99% for Boro; 0.062 MSE, 99% for wheat; and 0.016 MSE, 99% for potato production prediction. The Diebold-Mariano test is conducted to check the robustness of the proposed ensemble model, KRR. In most cases, it shows 1% and 5% significance compared to the benchmark ML models. Lastly, we design a recommender system that suggests suitable crops for a specific land area for cultivation in the next season. We believe that the proposed paradigm will help the farmers and personnel in the agricultural sector leverage proper crop cultivation and production.
农业是地球上粮食供应的最关键部门，它还负责为其他工业生产提供原材料。目前，农业生产的增长不足以跟上人口增长的步伐，这可能导致世界居民面临粮食短缺。因此，对于土地和资源有限的发展中国家来说，增加粮食产量至关重要。为了提高特定地区的作物产量，选择适合该地区的作物至关重要。需要基于历史数据（包括环境和种植面积以及作物产量）对该地区进行有效的作物产量预测。然而，此类预测数据并非公开可用。因此，在本文中，我们以一个发展中国家孟加拉国为例进行研究，该国经济依赖农业。我们首先从孟加拉国的相关研究机构收集并预处理数据，然后提出一种集成机器学习方法，称为K近邻随机森林岭回归（KRR），以有效预测主要作物（三种不同的水稻、土豆和小麦）的产量。KRR是在研究了五种现有的传统机器学习算法（支持向量回归、朴素贝叶斯和岭回归）和集成学习算法（随机森林和CatBoost）之后设计的。我们考虑四个经典评估指标，即平均绝对误差、均方误差（MSE）、均方根误差和[此处原文缺失一个指标]，以评估所提出的KRR相对于其他机器学习模型的性能。结果显示，对于Aus水稻，MSE为0.009，准确率为99%；对于Aman水稻，MSE为0.92，准确率为90%；对于Boro水稻，MSE为0.246，准确率为99%；对于小麦，MSE为0.062，准确率为99%；对于土豆产量预测，MSE为0.016，准确率为99%。进行迪博尔德 - 马里亚诺检验以检查所提出的集成模型KRR的稳健性。在大多数情况下，与基准机器学习模型相比，它显示出1%和5%的显著性水平。最后，我们设计了一个推荐系统，为下一季特定种植面积推荐适合种植的作物。我们相信所提出的范例将帮助农民和农业部门人员合理利用作物种植和生产。
