Tropical peatlands such as Ghana’s Greater Amanzule peatland are highly valuable ecosystems and under great pressure from anthropogenic land use activities. Accurate measurement of their occurrence and extent is required to facilitate sustainable management. A key challenge, however, is the high cloud cover in the tropics that limits optical remote sensing data acquisition. In this work we combine optical imagery with radar and elevation data to optimise land cover classification for the Greater Amanzule tropical peatland. Sentinel-2, Sentinel-1 and Shuttle Radar Topography Mission (SRTM) imagery were acquired and integrated to drive a machine learning land cover classification using a random forest classifier. Recursive feature elimination was used to optimize high-dimensional and correlated feature space and determine the optimal features for the classification. Six datasets were compared, comprising different combinations of optical, radar and elevation features. Results showed that the best overall accuracy (OA) was found for the integrated Sentinel-2, Sentinel-1 and SRTM dataset (S2+S1+DEM), significantly outperforming all the other classifications with an OA of 94%. Assessment of the sensitivity of land cover classes to image features indicated that elevation and the original Sentinel-1 bands contributed the most to separating tropical peatlands from other land cover types. The integration of more features and the removal of redundant features systematically increased classification accuracy. We estimate Ghana’s Greater Amanzule peatland covers 60,187 ha. Our proposed methodological framework contributes a robust workflow for accurate and detailed landscape-scale monitoring of tropical peatlands, while our findings provide timely information critical for the sustainable management of the Greater Amanzule peatland.

Pouteria campachiana is a multipurpose fruit tree with diverse economic and medicinal significance. However, seed dormancy and low germination are problems for its use in agro-forestry practices. Investigations were carried out on the effect of pre-treatment on the germination and early seedling growth of P. campachiana. Germination was observed in seeds pre-treated with soaking and mechanical scarification in the 5th week after sowing, while untreated seeds germinated in the 7th week. Comparison between mechanically scarified and unscarified P. campachiana seeds showed no significant difference (P > 0.05). The study showed that soaking P. campachina seeds in cold water was not good for its germination, with a significant difference between soaked seeds and non soaked seeds. Percentage germination of seeds not soaked was 62.2% compared to 26.7% and 24.4% recorded for seeds soaked for 24 h and 48 h, respectively. The application of different pre-treatments, however, had no significant (P > 0.05) influence on the mean shoot length, collar diameter, and the number of leaves of P. campachiana. The study concludes that mechanical scarification improves germination of P. campachiana while soaking with cold water has a negative influence on seed germination.

The Greater Amanzule Peatlands (GAP) in Ghana is an important biodiversity hotspot facing increasing pressure from anthropogenic land-use activities driven by rapid agricultural plantation expansion, urbanisation, and the burgeoning oil and gas industry. Accurate measurement of how these pressures alter land cover over time, along with the projection of future changes, is crucial for sustainable management. This study aims to analyse these changes from 2010 to 2020 and predict future scenarios up to 2040 using multi-source remote sensing and machine learning techniques. Optical, radar, and topographical remote sensing data from Landsat-7, Landsat-8, ALOS/PALSAR, and Shuttle Radar Topography Mission derived digital elevation models (DEMs) were integrated to perform land cover change analysis using Random Forest (RF), while Cellular Automata Artificial Neural Networks (CA-ANNs) were employed for predictive modelling. The classification model achieved overall accuracies of 93% in 2010 and 94% in both 2015 and 2020, with weighted F1 scores of 80.0%, 75.8%, and 75.7%, respectively. Validation of the predictive model yielded a Kappa value of 0.70, with an overall accuracy rate of 80%, ensuring reliable spatial predictions of future land cover dynamics. Findings reveal a 12% expansion in peatland cover, equivalent to approximately 6570 ± 308.59 hectares, despite declines in specific peatland types. Concurrently, anthropogenic land uses have increased, evidenced by an 85% rise in rubber plantations (from 30,530 ± 110.96 hectares to 56,617 ± 220.90 hectares) and a 6% reduction in natural forest cover (5965 ± 353.72 hectares). Sparse vegetation, including smallholder farms, decreased by 35% from 45,064 ± 163.79 hectares to 29,424 ± 114.81 hectares. Projections for 2030 and 2040 indicate minimal changes based on current trends; however, they do not consider potential impacts from climate change, large-scale development projects, and demographic shifts, necessitating cautious interpretation. The results highlight areas of stability and vulnerability within the understudied GAP region, offering critical insights for developing targeted conservation strategies. Additionally, the methodological framework, which combines optical, radar, and topographical data with machine learning, provides a robust approach for accurate and detailed landscape-scale monitoring of tropical peatlands that is applicable to other regions facing similar environmental challenges.

The Greater Amanzule Peatland (GAP) in Ghana represents an important ecosystem facing dynamic land cover changes as a result of both natural and anthropogenic factors. This study integrates multispectral and radar remote sensing data from Landsat-7 and -8, L-band SAR, and SRTM to conduct a machine learning-based analysis of these changes from 2010 to 2020 and to predict future scenarios up to 2040. Findings reveal a 12% expansion in peatland cover, equivalent to approximately 6,570 ± 308.59 hectares, despite declines in specific peatland types. Concurrently, anthropogenic land uses have increased, evidenced by an 85% rise in rubber plantations (from 30,530 ± 110.96 hectares to 56,617 ± 220.90 hectares) and a 6% reduction in natural forest cover (5,965 ± 353.72 hectares). Sparse vegetation, including smallholder farms, decreased by 35% from 45,064 ± 163.79 hectares to 29,424 ± 114.81 hectares. Projections for 2030 and 2040 indicate minimal changes based on current trends; however, these do not consider potential impacts from climate change, large-scale development projects, and demographic shifts, necessitating cautious interpretation. The results highlight areas of stability and vulnerability within the GAP and offer critical insights for the development of targeted conservation strategies. Additionally, the methodological framework presented provides a robust approach for accurate and detailed landscape-scale monitoring of tropical peatlands, applicable to other regions facing similar environmental challenges.

Accurate and spatially explicit habitat maps are essential for monitoring ecological change, supporting nature‐based solutions and informing policy. Despite advances in habitat mapping, classification accuracy varies across landscapes and thematic resolutions, highlighting the need for systematic evaluation of classification workflows. This study evaluates EcoservR, an open‐source rule‐based toolkit for habitat mapping, using field survey data from two contrasting landscapes in northern England: Merseyside (MER) and the North York Moors (NYM). Habitat classifications were generated by integrating multiple national spatial datasets and were evaluated against ecological survey records and high‐resolution aerial imagery across three levels of the Phase 1 habitat classification hierarchy developed by the Joint Nature Conservation Committee (JNCC). Overall accuracy ranged from 0.612 ± 0.015 (Level 3, NYM) to 0.804 ± 0.012 (Level 1, NYM). Broad habitat classes such as woodland and standing water achieved high precision, while grasslands, heathlands and mires showed lower precision. Accuracy declined with increasing thematic detail, reflecting ecological heterogeneity and limitations in the resolution and currency of input datasets. Observed land‐cover patterns corresponded with the known ecological structure of each landscape, although classification biases indicate that fine‐scale habitat assessments and quantitative ecosystem‐service estimates require supplementary data. Practical implications . EcoservR provides a reproducible workflow for integrating multiple spatial datasets to generate spatially consistent habitat maps. This approach supports regional planning and nature‐recovery initiatives where broad habitat categories are sufficient, and its rule‐based architecture allows adaptation to other landscapes where comparable datasets are available.

Extractive activities drive land transformation in many mineralised river basins. However, linking these changes to observable and attributable water-quality outcomes remains methodologically challenging. This study applies an integrated monitoring framework to examine how multi-decadal Land-use and land-cover change (LULC) translates into spatially differentiated river water quality in the Ankobra River basin, Ghana. Using harmonised Landsat and Sentinel imagery, LULC dynamics was reconstructed for 1986, 2002, 2016, and 2025. Field-based measurements of key physico-chemical water-quality parameters were collected to support the analysis. Spatial interpolation using Ordinary Kriging and redundancy analysis was then applied to assess the extent to which land-use composition explains the observed variation in water quality. The results showed a shift from forest-dominated land cover towards agriculture, settlement, and mining-related disturbance during the study period. Bareland/Mining expanded from less than 1% of the basin in 1986 to approximately 3.7% by 2025 (>100 km²), while combined forest cover declined overall throughout the study period. Water-quality patterns exhibited strong spatial gradients, with turbidity ranging from approximately 114 to more than 1000 NTU and total suspended solids (TSS) from around 100 to nearly 3000 mg L^-1. Redundancy analysis indicated that land-use composition explained approximately 47.5% of the variance in water quality, with the mining-related land cover exerting the strongest influence (F=13.66, p<0.001) and showing robust positive associations with turbidity and TSS. Closed forest cover displayed a significant buffering effect, while agricultural land use did not show significant association on the spatial scale examined. These findings demonstrate how integrated Earth observation and field data can move sustainability assessment beyond descriptive convergence towards diagnostic clarity. The analytical framework offers a transparent and scalable approach for prioritising regulatory attention and monitoring in extractive landscapes where environmental pressures are spatially uneven and governance capacity is constrained.