Understanding the drivers of community structure is fundamental for adequately managing ecosystems under global change. Here we used a large dataset of eighty-four headwater stream sites in three catchments in the Eastern Highlands of Zimbabwe, which represent a variety of abiotic conditions and levels of impairment, to examine the drivers of benthic macroinvertebrate community structure. We focused our assessment on macroinvertebrate family level community composition and functional feeding group classifications. Taxonomic richness was weakly positively correlated with ammonium, phosphates and pH, and weakly negatively correlated with detrital cover and dissolved oxygen. Measured abiotic variables, however, had limited influence on both macroinvertebrate diversity and functional feeding group structure, with the exception of ammonium, channel width and phosphates. This reflected the fact that many macroinvertebrate families and functional feeding guilds were well represented across a broad range of habitats. Predatory macroinvertebrates were relatively abundant, with collector-filterers having the lowest relative abundances. The findings of the study suggest that for certain ecological questions, a more detailed taxonomic resolution may be required to adequately understand the ecology of aquatic macroinvertebrates within river systems. We further recommend management and conservation initiatives on the Save River system, which showed significant impact from catchment developmental pressures, such as urbanisation, agriculture and illegal mining.
This study evaluates the Billion Tree Afforestation Project (BTAP) in Pakistan's Khyber Pakhtunkhwa (KPK) province using remote sensing and machine learning. Applying Random Forest (RF) classification to Sentinel-2 imagery, we observed an increase in tree cover from 25.02% in 2015 to 29.99% in 2023 and a decrease in barren land from 20.64% to 16.81%, with an accuracy above 85%. Hotspot and spatial clustering analyses revealed significant vegetation recovery, with high-confidence hotspots rising from 36.76% to 42.56%. A predictive model for the Normalized Difference Vegetation Index (NDVI), supported by SHAP analysis, identified soil moisture and precipitation as primary drivers of vegetation growth, with the ANN model achieving an R 2 of 0.8556 and an RMSE of 0.0607 on the testing dataset. These results demonstrate the effectiveness of integrating machine learning with remote sensing as a framework to support data-driven afforestation efforts and inform sustainable environmental management practices.