Modeling Spatiotemporal Patterns of Land Use/Land Cover Change in Central Malawi Using a Neural Network Model

The spatial heterogeneity of urban green space distribution and configuration in Lilongwe City, Malawi

Urban green spaces provide several benefits related to the quality of urban life. The existence and spatial arrangement of these spaces within neighbourhoods and functional land uses have significant implications for the well-being of urban dwellers. Previous studies on green spaces in urban areas of Malawi have focused on a broader and macro-level perspective, offering insightful information on general trends in different cities. However, there is a significant research shortage in localised understanding, which requires carrying out micro-level assessments concentrating on land use zones and neighbourhoods within these cities. In this study, we used remote sensing data and landscape metrics to understand the distribution and configuration of urban green spaces in the city's neighbourhoods and functional land uses and their relationship with urban form. The study revealed that 20% of neighbourhoods fail to meet the WHO-recommended standard of 9 m2 of green space per person, with a predominant concentration of these undersupplied areas in high-density and quasi-residential zones. In addition, 56.2% of Lilongwe City's total green area was contained under functional land uses. Particularly, high-rise residential, medium-density residential, low-density residential, quasi-residential, high-rise flat area, commercial class, high-rise commercial, heavy industry, light industry, and government land use zones contained 17.3%, 12.0%, 22.2%, 12.0%, 4.1%, 6.4%, 6.1%, 5.0%, 1.6%, and 13.3% of the total green spaces in functional land uses, respectively. Importantly, this research found significant correlations between urban form metrics, namely building coverage, building density, building perimeter area ratio, road density, and the distribution and configuration of urban green spaces. This necessitates an integrated approach to urban planning and design, emphasising the importance of balancing development with green space preservation.

Assessing changes in the ecosystem service value in response to land use and land cover dynamics in Malawi

Land use and land cover (LULC) changes are inevitable outcomes of socioeconomic changes and greatly affect ecosystem services. Our study addresses the critical gap in the existing literature by providing the first comprehensive national analysis of LULC changes and their impacts on ecosystem service values (ESVs) in Malawi. We assessed changes in ecosystem service values (ESVs) in response to LULC changes using the benefit transfer method in ArcGIS 10.6 software. Our findings revealed a significant increase in grasslands, croplands, and urban areas and a notable decline in forests, shrubs, wetlands, and water bodies. Grassland, cropland, and built-up areas expanded by 52%, 1%, and 23.2%, respectively. In contrast, permanent wetlands, barren land, and water bodies declined by 27.6%, 34.3%, and 1%, respectively. The ESV declined from US$90.87 billion in 2001 to US$85.60 billion in 2022, marking a 5.8% reduction. Provisioning services increased by 0.5% while regulating, supporting, and cultural ecosystem service functions declined by 12.2%, 3.16%, and 3.22%, respectively. The increase in provisioning services was due to the expansion of cropland. However, the loss of regulating, supporting, and cultural services was mainly due to the loss of natural ecosystems. Thus, environmental policy should prioritise the conservation and restoration of natural ecosystems to enhance the ESV of Malawi.

Monitoring and simulating landscape changes: how do long-term changes in land use and long-term average climate affect regional biophysical conditions in southern Malawi?

We set out to reveal the effects of long-term changes in land use and long-term average climate on the regional biophysical environment in southern Malawi. Object-oriented supervised image classification was performed on Landsat 5 and 8 satellite images from 1990 to 2020 to identify and quantify past and present land use-land cover changes using a support vector machine classifier. Subsequently, using 2000 and 2010 land use-land cover in an artificial neural network, land use-land cover for 2020 driven by elevation, slope, precipitation and temperature, population density, poverty, distance to major roads, and distance to villages data was simulated. Between 1990 and 2020, area of land cover increased in built-up (209%), bare land (10%), and cropland (10%) and decreased in forest (30%), herbaceous (4%), shrubland (20%), and water area (20%). Overall, the findings reveal that southern Malawi is dominantly an agro-mosaic landscape shaped by the combined effects of urban and agricultural expansions and climate. The findings also suggest the need to enhance the machine learning algorithms to improve capacity for landscape modelling and, ultimately, prevention, preparedness, and response to environmental risks.