Purpose

The internal (farmer-controlled) and external (non-farmer-controlled) factors affect crop yield. However, not a single study has identified and analyzed yield predictors in India using effective predictive models. Thus, this study aims to investigate how internal and external predictors impact pearl millet yield and Stover yield.

Design/methodology/approach

Descriptive analytics and artificial neural network are used to investigate the impact of predictors on pearl millet yield and Stover yield. From descriptive analytics, 473 valid responses were collected from semi-arid zone, and the predictors were categorized into internal and external factors. Multi-layer perceptron-neural network (MLP-NN) model was used in Statistical Package for the Social Sciences version 25 to model them.

Findings

The MLP-NN model reveals that rainfall has the highest normalized importance, followed by irrigation frequency, crop rotation frequency, fertilizers type and temperature. The model has an acceptable goodness of fit because the training and testing methods have average root mean square errors of 0.25 and 0.28, respectively. Also, the model has R² values of 0.863 and 0.704, respectively, for both pearl millet and Stover yield.

Research limitations/implications

To the best of the authors’ knowledge, the current study is first of its kind related to impact of predictors of both internal and external factors on pearl millet yield and Stover yield.

Originality/value

The literature reveals that most studies have estimated crop yield using limited parameters and forecasting approaches. However, this research will examine the impact of various predictors such as internal and external of both yields. The outcomes of the study will help policymakers in developing strategies for stakeholders. The current work will improve pearl millet yield literature.

中文翻译：

---

使用人工神经网络分析珍珠粟供应链的预测因子

目的

内部（农民控制）和外部（非农民控制）因素影响作物产量。然而，没有一项研究使用有效的预测模型来识别和分析印度的产量预测因素。因此，本研究旨在调查内部和外部预测因素如何影响珍珠粟产量和秸秆产量。

设计/方法论/途径

使用描述性分析和人工神经网络来研究预测变量对珍珠粟产量和秸秆产量的影响。通过描述性分析，从半干旱区收集了 473 个有效响应，并将预测因子分为内部因素和外部因素。社会科学统计包第 25 版使用多层感知器神经网络 (MLP-NN) 模型对其进行建模。

发现

MLP-NN 模型显示，降雨量具有最高的归一化重要性，其次是灌溉频率、轮作频率、肥料类型和温度。该模型具有可接受的拟合优度，因为训练和测试方法的平均均方根误差分别为 0.25 和 0.28。此外，该模型对于珍珠粟和秸秆产量的R ^{2值分别为 0.863 和 0.704。}

研究局限性/影响

据作者所知，目前的研究首次涉及内部和外部因素的预测因素对珍珠粟产量和秸秆产量的影响。

原创性/价值

文献表明，大多数研究都是使用有限的参数和预测方法来估计作物产量。然而，这项研究将研究各种预测因素的影响，例如两种收益率的内部和外部。研究结果将帮助政策制定者为利益相关者制定战略。当前的工作将提高珍珠粟产量文献。