The Impact of Technological Progress and Climate Change on Food Crop Production: Evidence from Sichuan-China

Statistical and machine learning models for location-specific crop yield prediction using weather indices

Crop yield prediction gains growing importance for all stakeholders in agriculture. Since the growth and development of crops are fully connected with many weather factors, it is inevitable to incorporate meteorological information into yield prediction mechanism. The changes in climate-yield relationship are more pronounced at a local level than across relatively large regions. Hence, district or sub-region-level modeling may be an appropriate approach. To obtain a location- and crop-specific model, different models with different functional forms have to be explored. This systematic review aims to discuss research papers related to statistical and machine-learning models commonly used to predict crop yield using weather factors. It was found that Artificial Neural Network (ANN) and Multiple Linear Regression were the most applied models. Support Vector Regression (SVR) model has a high success ratio as it performed well in most of the cases. The optimization options in ANN and SVR models allow us to tune models to specific patterns of association between weather conditions of a location and crop yield. ANN model can be trained using different activation functions with optimized learning rate and number of hidden layer neurons. Similarly, the SVR model can be trained with different kernel functions and various combinations of hyperparameters. Penalized regression models namely, LASSO and Elastic Net are better alternatives to simple linear regression. The nonlinear machine learning models namely, SVR and ANN were found to perform better in most of the cases which indicates there exists a nonlinear complex association between crop yield and weather factors.

Balancing agricultural production and environmental sustainability: Based on Economic Analysis From North China Plain

The escalating trend of greenhouse gas emissions presents a dual threat to both food security and the exacerbation of global warming. Addressing this pressing issue demands concerted efforts on local and global scales to champion sustainable food production and foster environmental benefits. In 2015, a pivotal field experiment was conducted in the North China Plain, aiming to delineate the intricate balance between agricultural productivity and environmental stewardship. This study comprised eight meticulously designed treatments, incorporating two key components: the evaluation of economic and environmental parameters encompassing carbon footprint, energy consumption, and the carbon sustainability index. Notably, while the carbon sustainability index exhibited improvement, it also revealed a 9.4% increase in emissions compared to the baseline, underscoring the nuanced trade-offs involved. The findings underscored the efficacy of no-tillage (NT) practices coupled with soybean-based crop rotation, mitigating yield reduction compared to conventional tillage (RT). However, the optimal yield was observed in the RT-MW treatment, amalgamating conventional tillage with minimum tillage practices. Moreover, despite the higher cost associated with soybeans relative to milled wheat, their cultivation yielded a notable increase in net income. These compelling results advocate for the adoption of conservation agriculture as a means to optimize the delicate equilibrium between environmental preservation and economic prosperity. Furthermore, the study underscores the imperative for further research endeavors aimed at devising highly productive agricultural systems that seamlessly integrate environmental sustainability with economic viability, echoing the crucial insights gleaned from analogous contexts.

Effect of Farmers' Awareness of Climate Change on Their Willingness to Adopt Low-Carbon Production: Based on the TAM-SOR Model

The COVID-19 pandemic highlighted the intricate relationships between human health and the social-ecological system in an era of climate and global change. Widespread COVID-19 adversely affected farmers' employment, production practices, and livelihood resilience. At the same time, climate change is a key issue limiting agricultural production worldwide. Emissions of greenhouse gases, such as carbon dioxide, are a major factor leading to global climate change. Greenhouse gas emissions from agricultural production are receiving increasing attention. Therefore, it is particularly important to develop low-carbon agriculture. Based on data from 920 family farms in Jiangsu province and Shaanxi province, this study constructs a structural equation model and empirically tests the relationship between the variables using the bootstrap method. The results show that: (1) climate change awareness did not directly stimulate farmers' willingness to pursue low-carbon production; (2) climate change awareness has an impact on low-carbon production willingness through perceived ease of use and consequence awareness; and (3) anti-risk ability can effectively moderate the impact of climate change awareness on low-carbon production behavior in agriculture. The theoretical model framework proposed in this study provides a reference for research in the field of low-carbon agriculture and also provides some insights and suggestions for environmentalists and governments. In addition, policymakers should effectively raise the sense of responsibility of farmers to address climate change and promote low-carbon agricultural production to achieve healthy and sustainable agricultural development.

Optimizing Agricultural Input and Production for Different Types of at-Risk Peasant Households: An Empirical Study of Typical Counties in the Yimeng Mountain Area of Northern China

Using typical counties in the Yimeng Mountain area of northern China as an example, this paper analyzed the household and agricultural input characteristics of different types of peasant households using survey data from 262 farm households. The target minimization of the total absolute deviations (MOTAD) model was applied to determine the optimal combinations in the allocation of agricultural input factors and production for different types of at-risk peasant households to obtain the ideal agricultural income. The relevant results are twofold. (1) The agricultural input behaviors of different types of peasant households vary significantly. The highest levels of agricultural land, labor, and yield-increasing and labor-saving inputs included I part-time peasant households (I PTPH), followed by full-time peasant households (FTPH), while the input levels of II part-time peasant households (II PTPH) and non-agricultural peasant households (NAPH) with higher levels of non-agricultural employment gradually decreased. In general, an increase in peasant households' part-time employment revealed an inverted U-shaped trend in the agricultural input level, with a trajectory of I PTPH > FTPH > II PTPH > NAPH. (2) The current agricultural inputs and production combinations of different types of peasant households have room for improvement. It is necessary to adjust agricultural inputs and optimize production combinations to obtain target incomes. Overall, all types of peasant households must streamline labor inputs and increase capital inputs, except for I PTPH, for which capital inputs should be reduced. Following optimization, economic crops gradually replace grain crops, and the optimal agricultural incomes of peasant households will be improved. The study results provide practical policy insights for reducing agricultural production risks and improving agricultural production incomes.