Crop mapping in smallholder farms using unmanned aerial vehicle imagery and geospatial cloud computing infrastructure.

Smallholder farms are major contributors to agricultural production, food security, and socio-economic growth in many developing countries. However, they generally lack the resources to fully maximize their potential. Subsequently they require innovative, evidence-based and lower-cost solutions to optimize their productivity. Recently, precision agricultural practices facilitated by unmanned aerial vehicles (UAVs) have gained traction in the agricultural sector and have great potential for smallholder farm applications. Furthermore, advances in geospatial cloud computing have opened new and exciting possibilities in the remote sensing arena. In light of these recent developments, the focus of this study was to explore and demonstrate the utility of using the advanced image processing capabilities of the Google Earth Engine (GEE) geospatial cloud computing platform to process and analyse a very high spatial resolution multispectral UAV image for mapping land use land cover (LULC) within smallholder farms. The results showed that LULC could be mapped at a 0.50 m spatial resolution with an overall accuracy of 91%. Overall, we found GEE to be an extremely useful platform for conducting advanced image analysis on UAV imagery and rapid communication of results. Notwithstanding the limitations of the study, the findings presented herein are quite promising and clearly demonstrate how modern agricultural practices can be implemented to facilitate improved agricultural management in smallholder farmers.

Quantitative remote sensing of forest ecosystem services in sub-Saharan Africa's urban landscapes: a review.

A dearth of information on urban ecosystem services in the past decades has led to little consolidation of such information for informed planning, decision-making and policy development in sub-Saharan African cities. However, the increasing recognition of the value of urban ecological processes and services as well as their contribution to climate change adaptation and mitigation has recently become an area of great research interest. Specifically, the emerging geospatial analytical approaches like remote sensing have led to an increase in the number of studies that seek to quantify and map urban ecosystem services at varying scales. Hence, this study sought to review the current remote sensing trends, challenges and prospects in quantifying urban ecosystem services in sub-Saharan Africa cities. Literature shows that consistent modelling and understanding of urban ecosystem services using remotely sensed approaches began in the 1990s, with an average of five publications per year after around 2010. This is mainly attributed to the approach's ability to provide fast, accurate and repeated spatial information necessary for optimal and timely quantification and mapping of urban ecosystem services. Although commercially available high spatial resolution sensors (e.g. the Worldview series, Quickbird and RapidEye) with higher spatial and spectral properties have been valuable in providing highly accurate and reliable data for quantification of urban ecosystem services, their adoption has been limited by high image acquisition cost and small spatial coverage that limits regional assessment. Thus, the newly launched sensors that provide freely and readily available data (i.e. Landsat 8 and 9 OLI, Sentinel-2) are increasingly becoming popular. These sensors provide data with improved spatial and spectral properties, hence valuable for past, current and future urban ecosystem service assessment, especially in developing countries. Therefore, the study provides guidance for future studies to continuously assess urban ecosystem services in order to achieve the objectives of Kyoto Protocol and Reducing Emissions from Deforestation and forest Degradation (REDD +) of promoting climate-resilient and sustainable cities, especially in developing world.

Estimating aboveground net primary productivity of reforested trees in an urban landscape using biophysical variables and remotely sensed data.

Recently, urban reforestation programs have emerged as potential carbon sinks and climate mitigates in urban landscapes. Thus, spatially explicit information on net primary productivity (NPP) of reforested trees in urban environments is central to understanding the value of reforestation initiatives in the global carbon budget and climate regulation potential. To date, numerous studies have mainly focused on natural and commercial forests NPP at a regional scale based on coarse spatial resolution remotely sensed data. Generally, local scale NPP studies based on fine spatial resolution data are limited. Therefore, this study sought to estimate aboveground NPP of an urban reforested landscape using biophysical and Sentinel-2 Multispectral Imager data derived variables. Using the MOD17 model, results showed that mean NPP ranged between 6.24 Mg C ha-1 with high coefficient of determination (R2: 0.92) and low RMSE (0.82 Mg ha-1) across all reforested trees within the study area. Results also showed a considerable variation in NPP among the reforested trees, with deciduous Acacia and Dalbergia obovate species showing the highest NPP (7.62 Mg C ha-1 and 7.58 Mg C ha-1, respectively), while the evergreen Syzygium cordatum and shrub Artemisia afra had the lowest NPP (4.54 Mg C ha-1 and 5.26 Mg C ha-1). Furthermore, the multiple linear regression analysis showed that vegetation specific biophysical variables (i.e. leaf area index, Normalized Difference Vegetation Index and Fraction of Photosynthetically Active Radiation) significantly improved the estimation of reforested aboveground NPP at a fine-scale resolution. These findings demonstrate the effectiveness of biophysical and remotely sensed variables in determining NPP (as carbon sequestration surrogate) at fine-scaled reforested urban landscape. Furthermore, the utility of species biometric measurements and MOD17 model offers unprecedented opportunity for improved local scale reforestation assessment and monitoring schedules.

Deep learning approaches in remote sensing of soil organic carbon: a review of utility, challenges, and prospects.

The use of neural network (NN) models for remote sensing (RS) retrieval of landscape biophysical and biochemical properties has become popular in the last decade. Recently, the emergence of "big data" that can be generated from remotely sensed data and innovative machine learning (ML) approaches have provided a platform for novel analytical approaches. Specifically, the advent of deep learning (DL) frameworks developed from traditional neural networks (TNN) offer unprecedented opportunities to improve the accuracy of SOC retrievals from remotely sensed imagery. This review highlights the use of TNN models and their evolution into DL architectures in remote sensing of SOC estimation. The review also highlights the application of DL, with a specific focus on its development and adoption in remote sensing of SOC mapping. The review concludes by highlighting future opportunities for the use of DL frameworks for the retrieval of SOC from remotely sensed data.

Characterizing bracken fern phenological cycle using time series data derived from Sentinel-2 satellite sensor.

Bracken fern is an invasive plant that has caused serious disturbances in many ecosystems due to its ability to encroach into new areas swiftly. Adequate knowledge of the phenological cycle of bracken fern is required to serve as an important tool in formulating management plans to control the spread of the fern. This study aimed to characterize the phenological cycle of bracken fern using NDVI and EVI2 time series data derived from Sentinel-2 sensor. The TIMESAT program was used for removing low quality data values, model fitting and for extracting bracken fern phenological metrics. The Sentinel-2 satellite-derived phenological metrics were compared with the corresponding bracken fern phenological events observed on the ground. Findings from our study revealed that bracken fern phenological metrics estimated from satellite data were in close agreement with ground observed phenological events with R2 values ranging from 0.53-0.85 (p < 0.05). Although they are comparable, our study shows that NDVI and EVI2 differ in their ability to track the phenological cycle of bracken fern. Overall, EVI2 performed better in estimating bracken fern phenological metrics as it related more to ground observed phenological events compared to NDVI. The key phenological metrics extracted in this study are critical for improving the precision in the controlling of the spread of bracken fern as well as in implementing active protection strategies against the invasion of highly susceptible rangelands.

Correction: Multi-criteria suitability analysis for neglected and underutilised crop species in South Africa.

[This corrects the article DOI: 10.1371/journal.pone.0244734.].

Multi-criteria suitability analysis for neglected and underutilised crop species in South Africa.

Several neglected and underutilised species (NUS) provide solutions to climate change and creating a Zero Hunger world, the Sustainable Development Goal 2. Several NUS are drought and heat stress-tolerant, making them ideal for improving marginalised cropping systems in drought-prone areas. However, owing to their status as NUS, current crop suitability maps do not include them as part of the crop choices. This study aimed to develop land suitability maps for selected NUS [sorghum, (Sorghum bicolor), cowpea (Vigna unguiculata), amaranth and taro (Colocasia esculenta)] using Analytic Hierarchy Process (AHP) in ArcGIS. Multidisciplinary factors from climatic, soil and landscape, socio-economic and technical indicators overlaid using Weighted Overlay Analysis. Validation was done through field visits, and area under the curve (AUC) was used to measure AHP model performance. The results indicated that sorghum was highly suitable (S1) = 2%, moderately suitable (S2) = 61%, marginally suitable (S3) = 33%, and unsuitable (N1) = 4%, cowpea S1 = 3%, S2 = 56%, S3 = 39%, N1 = 2%, amaranth S1 = 8%, S2 = 81%, S3 = 11%, and taro S1 = 0.4%, S2 = 28%, S3 = 64%, N1 = 7%, of calculated arable land of SA (12 655 859 ha). Overall, the validation showed that the mapping exercises exhibited a high degree of accuracies (i.e. sorghum AUC = 0.87, cowpea AUC = 0.88, amaranth AUC = 0.95 and taro AUC = 0.82). Rainfall was the most critical variable and criteria with the highest impact on land suitability of the NUS. Results of this study suggest that South Africa has a huge potential for NUS production. The maps developed can contribute to evidence-based and site-specific recommendations for NUS and their mainstreaming. Also, the maps can be used to design appropriate production guidelines and to support existing policy frameworks which advocate for sustainable intensification of marginalised cropping systems through increased crop diversity and the use of stress-tolerant food crops.

Scribbling the Cat: A Case of the "Miracle" Plant, Moringa oleifera.

This paper reviews the properties of the most cultivated species of the Moringaceae family, Moringa oleifera Lam. The paper takes a critical look at the positive and the associated negative properties of the plant, with particular emphasis on its chemistry, selected medicinal and nutritional properties, as well as some ecological implications of the plant. The review highlights the importance of glucosinolates (GS) compounds which are relatively unique to the Moringa species family, with glucomoriginin and its acylated derivative being the most abundant. We highlight some new research findings revealing that not all M. oleifera cultivars contain an important flavonoid, rutin. The review also focuses on phenolic acids, tannin, minerals and vitamins, which are in high amounts when compared to most vegetables and fruits. Although there are numerous benefits of using M. oleifera for medicinal purposes, there are reports of contraindications. Nonetheless, we note that there are no major harmful effects of M. oleifera that have been reported by the scientific community. M. oleifera is suspected to be potentially invasive and moderately invasive in some regions of the world because of its ability to grow in a wide range of environmental conditions. However, the plant is currently classified as a low potential invasive species and thus there is a need to constantly monitor the species. Despite the numerous benefits associated with the plant, there is still a paucity of data on clinical trials proving both the positive and negative effects of the plant. We recommend further clinical trials to ascertain the properties associated with the plant, especially regarding long term use.