Purpose

The damping accumulated discrete MGM(1, m) power model is proposed for the problem of forecasting the share of agricultural output value and the share of employment in China.

Design/methodology/approach

In this study, the damping accumulated discrete MGM(1, m) power model was developed based on the idea of discrete modelling by introducing a damping accumulated generating operator and power index. The new model can better identify the non-linear characteristics existing between different factors in the multivariate system and can accurately describe and forecast the trend of changes between data series and each of them.

Findings

The validity and rationality of the new model are verified through numerical experiment. It is forecasted that in 2023, the share of agricultural output value in China will be 7.14% and the share of agricultural employment will be 21.98%, with an overall decreasing trend.

Practical implications

The simultaneous decline in the share of agricultural output value and the share of employment is a common feature of countries that have achieved agricultural modernisation. Accurate forecasts of the share of agricultural output value and the share of employment can provide an important scientific basis for formulating appropriate agricultural development targets and policies in China.

Originality/value

The new model proposed in this study fully considers the importance of new information and has higher stability. The differential evolutionary algorithm was used to optimise the model parameters.

中文翻译：

---

阻尼累积离散MGM(1, m)幂模型及其在农业产值份额和就业份额预测中的应用

目的

针对我国农业产值比重和就业比重的预测问题，提出了阻尼累积离散MGM(1, m)幂模型。

设计/方法论/途径

本研究基于离散建模思想，引入阻尼累积发电算子和功率指标，建立了阻尼累积离散MGM(1, m)功率模型。新模型能够更好地识别多元系统中不同因素之间存在的非线性特征，能够准确地描述和预测数据序列之间以及各个因素之间的变化趋势。

发现

通过数值实验验证了新模型的有效性和合理性。预计2023年，我国农业产值比重为7.14%，农业就业比重为21.98%，总体呈下降趋势。

实际影响

农业产值比重和就业比重同时下降，是实现农业现代化国家的共同特点。准确预测农业产值比重和就业比重，可以为我国制定适当的农业发展目标和政策提供重要的科学依据。

原创性/价值

本研究提出的新模型充分考虑了新信息的重要性，具有更高的稳定性。采用差分进化算法对模型参数进行优化。