Smallholder farmers cultivate more than 80% of the cropland area available in Africa. The intrinsic characteristics of such farms include complex crop-planting patterns, and small fields that are vaguely delineated. These characteristics pose challenges to mapping crops and fields from space. In this study, we evaluate the use of a cloud-based multi-temporal ensemble classifier to map smallholder farming systems in a case study for southern Mali. The ensemble combines a selection of spatial and spectral features derived from multi-spectral Worldview-2 images, field data, and five machine learning classifiers to produce a map of the most prevalent crops in our study area. Different ensemble sizes were evaluated using two combination rules, namely majority voting and weighted majority voting. Both strategies outperform any of the tested single classifiers. The ensemble based on the weighted majority voting strategy obtained the higher overall accuracy (75.9%). This means an accuracy improvement of 4.65% in comparison with the average overall accuracy of the best individual classifier tested in this study. The maximum ensemble accuracy is reached with 75 classifiers in the ensemble. This indicates that the addition of more classifiers does not help to continuously improve classification results. Our results demonstrate the potential of ensemble classifiers to map crops grown by West African smallholders. The use of ensembles demands high computational capability, but the increasing availability of cloud computing solutions allows their efficient implementation and even opens the door to the data processing needs of local organizations.

Interactive Planning Support Systems (PSS) implemented on a maptable are deemed suitable to support participatory planning processes. They are supposed to facilitate exchange of knowledge between stakeholders, consensus building among them, and group-learning processes. In this systematic review, based on 16 case studies using interactive PSS, we analyze how these have contributed to the goal of strengthening stakeholder participation. To this end, we first elicit details of the interactive PSS and the related participatory processes. In the second step, we analyze how and what the studies report, as the impacts on participation. Results show that tools and applications have become more sophisticated over time and goals of the studies changed from collaboratively designing interventions to observing and understanding how the application of such tools contributes to improved plan outcomes and group-based learning. All interactive PSS succeeded to facilitate intensive stakeholder collaboration. However, many studies lack a proper framework for investigating its impacts on participation and therefore assess these rather incidentally based on implicit assumptions. Thus, a significant outcome of this review is an evaluation framework, which allows the structural assessment of the impacts of interactive PSS on stakeholder participation.

Changes in commodity prices, such as the fall in coffee prices from 2000 to 2004, affect land use decisions on farms, and the environmental services they provide. A survey of 50 farms showed a 35% loss in the area under coffee between 2000 and 2004 below 700 m with the majority of this area (64 %) being coffee agroforest systems that included native forest species. Loss of coffee only occurred on large and medium-scale farms; there was no change in area on cooperatives. Coffee productivity declined below 1,100 m altitude for sun and Inga shade coffee, but only below 700 m altitude for agroforest coffee. Coffee productivity was 37-53% lower under agroforests than other systems. Increases in rubber and pasture were related to low altitude large-scale farms, and bananas and timber plantations to mid-altitude farms. Average aboveground carbon stocks for coffee agroforests of 39 t C ha(-1) was similar to rubber plantations, but one-third to one half that of natural forest and timber plantations, respectively. Coffee agroforests had the highest native tree diversity of the productive systems (7-12 species ha(-1)) but lower than natural forest (31 species ha(-1)). Conversion of coffee agroforest to other land uses always led to a reduction in the quality of habitat for native biodiversity, especially avian, but was concentrated among certain farm types. Sustaining coffee agroforests for biodiversity conservation would require targeted interventions such as direct payments or market incentives specifically for biodiversity.

Geospatial data is urgently needed in decision-making processes to achieve Sustainable Development Goals (SDGs) at global, national, regional and local scales. While the advancement of geo-technologies to obtain or produce geospatial data has become faster and more affordable, many countries in the global south still experience a geospatial data scarcity at the rural level due to complex geographical terrains, weak coordination among institutions and a lack of knowledge and technologies to produce visualised geospatial data like maps. We proposed a collaborative spatial learning framework that integrates the spatial knowledge of stakeholders to obtain geospatial data. By conducting participatory mapping workshops in three villages in the Deli Serdang district in Indonesia, we tested the framework in terms of facilitating communication and collaboration of the village stakeholders while also supporting knowledge co-production and social learning among them. Satellite images were used in digital and non-digital mapping workshops to support village stakeholders to produce proper village maps while fulfilling the SDGs’ emphasis to make geospatial data available through a participatory approach.

Open spaces are essential for promoting quality of life in cities. However, accelerated urban growth, in particular in cities of the global South, is reducing the often already limited amount of open spaces with access to citizens. The importance of open spaces is promoted by SDG indicator 11.7.1; however, data on this indicator are not readily available, neither globally nor at the metropolitan scale in support of local planning, health and environmental policies. Existing global datasets on built-up areas omit many open spaces due to the coarse spatial resolution of input imagery. Our study presents a novel cloud computation-based method to map open spaces by accessing the multi-temporal high-resolution imagery repository of Planet. We illustrate the benefits of our proposed method for mapping the dynamics and spatial patterns of open spaces for the city of Kampala, Uganda, achieving a classification accuracy of up to 88% for classes used by the Global Human Settlement Layer (GHSL). Results show that open spaces in the Kampala metropolitan area are continuously decreasing, resulting in a loss of open space per capita of approximately 125 m2 within eight years.