Prediction of the Hemp Yield Using Artificial Intelligence Methods

ABSTRACT

The aim of this study was to determine the usefulness of artificial neural networks (ANN) in the process of forecasting the yield of hemp seeds (Cannabis sativa L.) of the Henola variety. The field experiments (various doses of mineral fertilization, sowing date, row spacing) results were also used to generate neural models. The highest straw (15.90 Mg∙ha⁻¹) and seed (2.93 Mg∙ha⁻¹) yield were obtained for the highest dose of mineral fertilization and sowing date at the turn of April and May in Wielkopolska Region resulted in the highest yields of both straw (14.70 Mg∙ha⁻¹) and seeds (2.66 Mg∙ha⁻¹). As a result of the conducted research, two linear models of ANN s were generated. The 4: 8–1: 1 model, used to forecast the seed yield was characterized by an accuracy of nearly 91%, and the RMSPE error less than 34%. The second model, the 4: 4–1: 1 network, was used to forecast the straw yield and had The test quality nearly 74%, and the RMSPE error 26%.

ABSTRACT

摘要

本研究的目的是确定人工神经网络 (ANN) 在预测Henola品种大麻种子产量过程中的有用性. 田间试验 (不同施肥剂量, 播种期, 行距) 结果也用于生成神经模型. 最高吸管 (15.90 Mg∙ha-1) 和种子 (2.93 Mg∙在4月和5月初的Wielkopolska地区, 矿质肥料和播种期的最高剂量获得了ha-1的产量, 这两种秸秆的产量最高 (14.70mg/kg) ∙ha-1) 和种子 (2.66 Mg∙ha-1) . 作为研究的结果, 生成了两个神经网络的线性模型。用于预测种子产量的4:8-1:1模型的精度接近91%, RMSPE误差小于34%. 第二个模型是4:4-1:1网络, 用于预测秸秆产量, 测试质量接近74%, RMSPE误差26%.

KEYWORDS:

• Yield forecasting
• hemp cultivation
• artificial neural networks
• parameters of affecting yield
• Cannabis sativa
• hemp seed
• hemp straw

关键词:

• 产量预测
• 大麻种植
• 人工神经网络
• 影响产量的参数
• 大麻
• 大麻籽
• 大麻吸管

Highlights

1. The linear models of ANN can be useful in process if forecasting the yield of hemp seed and straw.

2. Possibilities of neural modeling methods application in hemp yield forecasting process.

3. Cultivation and sowing parameters characteristic of hemp cultivation affecting the yield.

4. Research on the possibility of using ANN in agriculture practice should be developed by increasing the amount of data and supplementing the information with further describing variables, which should improve the quality of the tested models and have a positive impact on the reduction of error.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Ethical approval

We confirm that all the research meets ethical guidelines and adheres to the legal requirements of the study country. The research does not involve any human or animal welfare related issues.

Additional information

Funding

This article was prepared as a result of the realization of the project entitled: “Evaluation of neural modeling methods in predicting the quality and quantity of the hemp yield.” financed by the Ministerstwo Rolnictwai Rozwoju Wsi (Polish Ministry of Agriculture and Rural Development- contract number DSR.nw.070.4.2021