This study aimed to determine the impacts of climate variability on smallholder maize producers’ water use behaviour and the factors that influence their decision-making in the Vhembe District Municipality, Limpopo Province, South Africa. This study utilized a survey from 366 smallholder maize irrigators, Theory of Planned Behaviour (TPB), and Structural Equation Modelling (SEM). The TPB posits that behavioural intentions can influence actual behaviour of individuals and groups, and it consists of three behavioural factors, namely attitude, subjective norms, and perceived behavioural control. Findings indicated that most of the farmers (96%) in the study area were dependent on farming as their primary occupation and livelihood. Most of the farmers were senior citizens with the mean age being between 51–60 and above 61 years of age, majority of the respondents (71%) had secondary education level and majority of the farmers (40%) had less than 10 years of farming experience and 35% had between 11–20 years of farming experience. In addition, the findings revealed that attitude, subjective norms, and perceived behavioural control significantly influence the small-scale farmers’ intentions to adapt to climate variability. The results suggest that as farmers’ attitudes become positive, their intentions to adapt enhance, and the perceptions of adaptation behaviours have a significant impact on individual farmers’ willingness to adapt. In addition, attitude and subjective norms have a substantial influence on the intentions of behavioural changes of farmers’ adaptation. However, perceived behavioural control does influence Intention but has a minor impact compared to attitudes and norms. Therefore, socio-psychological issues should be taken into consideration to improve smallholder farmers’ adoption of sustainable water use practices. This could raise smallholders’ livelihoods and agricultural productivity.
Rachel M. Msila, Y. Bahta, H. Jordaan et al.· PLoS ONE· 0 citations
Artificial intelligence (AI) is increasingly applied in agriculture to support data-driven decision-making, improve productivity, and enhance resource management. Small-scale farmers, who produce a significant share of the world’s food yet often operate under resource constraints, may particularly benefit from these technologies. However, it remains unclear how AI research addresses the needs of small-scale farming systems and the extent to which farmers directly interact with AI tools. This study conducts a systematic literature review to examine the applications, impacts, and challenges of AI in small-scale agriculture. The review followed the PRISMA 2020 guidelines and applied a structured review methodology, using the Web of Science, Scopus, and EBSCOhost databases. A total of 182 studies were identified and analyzed. The results show a rapid increase in publications after 2020, with research concentrated mainly in Africa and Asia. Most studies focus on technical AI applications such as plant disease detection, crop yield prediction, crop classification, and environmental monitoring, commonly using machine learning and deep learning techniques. However, only a small number of studies examine farmers’ direct interaction with AI systems, including adoption, perceptions, and practical usage. This imbalance indicates that the literature remains largely technology-driven rather than farmer-centred. The review highlights important research gaps, particularly in farmer engagement, integrated farm management applications, and the translation of AI prototypes into scalable solutions. Future research should prioritize participatory approaches and context-sensitive AI systems to ensure that technological advances effectively support small-scale farmers and sustainable agricultural development.
Zimbini Coka, M. Monteiro, B. Jammer· Agriculture· 0 citations