Globally, Smallholder farming systems (SFS) are recognized as one of the most important pillars of rural economic development and poverty alleviation because of their contribution to food security. However, support for this agricultural sector is hampered by lack of reliable information on the distributions and acreage of smallholder fields. This information is essential in not only monitoring food security and informing markets but also in guiding the determination of levels of support required from government by individual farmers. There is urgent need for robust techniques that can be used to cost-effectively and time-efficiently map smallholder crop fields especially in Sub-Saharan Africa and Asia. This study attempts to do this by using an approach in which optical and Synthetic Aperture Radar (SAR) data are systematically combined and classified using Extreme Gradient Boosting (Xgboost). We also investigated model stacking as another technique to improve classification accuracy. We combined Xgboost with Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Networks (ANN), and Naïve Bayes (NB). The combined use of multi-temporal Sentinel-2 bands, spectral indices, and Sentinel-1 produced better results than exclusive use of optical data (α = 0.95, p = 0.0005). Furthermore, stacking of classification algorithms based on model comparisons achieved higher accuracy than stacking the algorithms indiscriminately (α = 0.95, p = 0.0100). Through systematic fusion of SAR and optical data and hyper-parameter tuning of Xgboost, we achieved a maximum classification accuracy of 97.71%, while achieving a maximum accuracy of 96.06% through model stacking. This highlights the importance of multi-sensor data fusion and multi-classifier systems when mapping fragmented agricultural landscapes.

No abstract

While the devastating vagaries of climate change are ravaging communities the world over, especially in Africa, and Zimbabwe in particular, the role of traditional authorities is being overlooked. This paper argues for a relentless push towards the unimpeded involvement of local traditional authorities (LTAs) in the mobilisation of rural communities to adopt appropriate climate change adaptation practices in Zimbabwe. Given its complexity and uniqueness, external intervention through government and non-governmental agents alone can hardly foster climate change adaptation particularly at local levels within communities. Traditional leaders, who have for a long time been useful in the governance of people in various rural communities, can play a supportive role in climate change adaptation. Traditional leaders do not only serve as governance authorities but also know the traditional strategies of combating the negative effects of climate change. Despite the pressure from political interference and the advent of western technological advancement, a lot could still be done to buttress the authority and respect vested in chiefs, headsmen and village heads in the country. LTAs have the power to manage grassroots communities; hence they can be utilised as drivers in the use of traditional climate change adaptation strategies. The paper concludes that political interference is one challenge faced by abusing traditional leadership as a means to gain political mileage. The paper recommends for extended capacity building on the part of traditional leaders to improve their knowledge base. This will enable them to appreciate the integration of indigenous and modern climate change adaptation strategies. It further recommends the revitalisation of the traditional council (Dare raMambo) to deal with environmental offenses with the scope of assisting government efforts to ensure sound ecological practices within communities.

This article reports on a study that analysed a myriad of adaptation practices adopted by smallholder farmers in Chimanimani District, Zimbabwe. Using a predominantly qualitative design, some in-depth interviews were conducted with purposefully selected key respondents. Focus group discussions with 8 to 12 smallholder farmers per group were conducted in each of the district’s 22 wards. These were corroborated by the guided observation method. The data was analysed using thematic content analysis, where broad strands of responses were synthesised and condensed into narrow themes that made them easier to interpret. Accordingly, smallholder farmers opted for drought tolerant crop and animal species, indigenous seed preservation techniques, aquaculture and conservation farming. The off-farm practices included craftwork, bee-keeping, artesian mining and trade. The sustainable livelihoods framework (SLF) was used as an analytical lens to appraise the sustainability of smallholder farmers’ choices and practices. Therefore, as farmers switched from one practice to another, many of their adaptive options reflected short-term livelihood benefits with concealed medium- to long-term environmental detriments. Strangely, some malpractices have their roots in short-sighted government policy frameworks mainstreamed to alleviate grass roots poverty. A thorough evaluation of adaptive policies is recommended so as to strengthen the adaptive capacity of smallholder farmers against the background of climate change.

The global sustainability agenda provides the opportunity for higher education institutions to mainstream the Sustainable Development Goals into their programmes to contribute towards achieving these goals. Using an inquiry-based research approach, underpinned by constructivism, this study aimed to determine how research concepts and research skills can be integrated effectively into a first-year module through inquiry-based learning. First-year students at a South African university were assigned research tasks to analyse journal articles and compile a summative project based on observations in urban ecosystems. Using a mixed-methods approach, data were collected via online, structured questionnaires, reflective practice schedules and semi-structured interviews. Data were analysed quantitatively using descriptive statistics and supported by qualitative analysis of open-ended responses. Some of the findings included main skills developed, communication and social skills; main challenges experienced, finding a study site and working with a partner; the research task was relevant to career and society, and enhanced understanding of the module content. The integration of research at undergraduate level fostered environmental stewardship, positive career aspirations, motivation to pursue further research, and promoted problem-solving to real-world problems. It is recommended that universities support more undergraduate programmes to adopt inquiry-based learning within authentic research tasks.