Identifying Categorical Land Use Transition and Land Degradation in Northwestern Drylands of Ethiopia

Dynamics and Drivers of Land Use and Land Cover Change in the Upper Awash Basin, Central Rift Valley of Ethiopia

This study analyzed the patterns and drivers of LULC dynamics in relation to the expansion of large-scale irrigated agriculture in the Central Rift Valley of Ethiopia from 1972 to 2016. Aerial photographs (1972), Landsat images (1980, 2000) and SPOT5 satellite images (2016) were analyzed using GIS tools to reveal LULC changes, and documentation, key informant interviews and focus group discussions were used to ascertain the biophysical and socioeconomic implications and drivers of these dynamics. The study revealed that cultivated and rural settlement land, and urban built-up areas had expanded at the expense of forestland, woodland, shrubland and grassland. While an increase in the production of cash crops had brought some benefits to smallholder farmers, such as access to irrigation and modern agricultural inputs and technologies, the unregulated conversion of natural vegetation to cultivated land resulted in a loss of biodiversity, deforestation, and reduction of pasture and firewood. We identified that significant LULC changes in the study area were caused by intersecting biophysical, economic, institutional, technological and demographic factors, which reinforced each other with varying magnitudes at different moments in time. These changes were underpinned by one key driver, that is, government agricultural policies that promoted investment in commercial agriculture for national and export markets. The study shows that understanding the complex interaction between the contributing factors and drivers of LULC change is crucial to inform decision-making and policies, in particular, by directing responses towards the underlying drivers of change rather than only the proximate causes.

Land use and land cover dynamics and ecosystem services values in Kewet district in the central dry lowlands of Ethiopia

A better comprehensive and quantitative analysis of the tempo-spatial dynamics of land use and cover (LULC) in the dry lowlands areas of Ethiopia is crucial for restoring degraded landscapes. This study aimed at analyzing the trends of LULC changes and determine their ecosystem service values in Kewet district central dry lowlands of Ethiopia using multi-temporal satellite imagery for three periods: 1995, 2008, and 2017. Supervised classification, using the maximum likelihood classifier, was applied to quantify LULC changes. Ecosystem Service values were estimated using the modified ecosystem service value coefficients. LULC analysis showed that cultivated land was the most predominant which covered over 41% of the study area in all three periods. Forests showed a net increase of 18.2%. Shrubland occupied the second largest portion in all LULC analysis next to cultivated land, and it showed a net decrease of 29.2%. Open grassland showed a periodic increase. Over the past 20 years, built-up area and bared land grew continuously by 1.80 and 1.01 km² yr^-1, respectively. However, some degraded land was converted into woody vegetation land through area exclosure, which improved the vegetation coverage of the study area. Ecosystem Service values ranged from US$ 2.37 million for shrubland in 1995 to US$ 22.49 million for forest land in 2008. The total ESVs of the district also continuously decreased over the past two decades. Generally, the LULC in the Kewet district has been dynamic in that some of the LULC classes were expanding, while the others were shrinking through time.

Mapping Land Use Land Cover Changes and Their Determinants in the Context of a Massive Free Labour Mobilisation Campaign: Evidence from South Wollo, Ethiopia

Northern Ethiopia is characterised by fragile mountain eco-systems that are highly susceptible to land degradation, impacting food security and livelihoods. This study appraises Land Use Land Cover Changes (LULCC) and their determinants from 2000 to 2020 in Dessie Zuria and Kutaber Woredas. It explores the LULCC and the key anthropogenic drivers of the change over the past 20 years through a mix of satellite imagery and a survey of local understandings. Six land use types (agriculture, forest, area closure, grazing, settlement and bare land) were mapped from satellite imagery that was acquired from Landsat 7 for the years 2000, 2005, and 2010, and Landsat 8 and OLI multispectral imageries for the years 2015 and 2020 with a spectral resolution of 30-m obtained from USGS. The results showed that agricultural land increased from 29.68% in 2000 to 35.77% in 2020.Furthermore, settlement and grazing lands enlarged from 5.95% and 6.04%, respectively, to 8.31% and 6.35% during the same period, while bare land increased from 9.89% to 10.92% in 2020. On the contrary, forest and area closure decreased from 18.45% and 29.99% to 17.8% and 17.38%, respectively. Meanwhile, population growth, unrestricted grazing, losing a sense of ownership of protected area closures and forests, lack of cooperation, using the free labour mobilisation schemes for government-induced agendas, weak enforcement of laws and bylaws, and engaging farmers for extended days on the campaign were prominent determinants of the changes. This research has implications for development actors across land management and food security towards implementing sustainable land management in the area and beyond.

Computer Vision Framework for Wheat Disease Identification and Classification Using Jetson GPU Infrastructure

Diseases have adverse effects on crop production and yield loss. Various diseases such as leaf rust, stem rust, and strip rust can affect yield quality and quantity for a studied area. In addition, manual wheat disease identification and interpretation is time-consuming and cumbersome. Currently, decisions related to plants mainly rely on the level of expertise in the domain. To resolve these challenges and to identify wheat disease as early as possible, we implemented different deep learning models such as Inceptionv3, Resnet50, and VGG16/19. This research was conducted in collaboration with Bishoftu Agricultural Research Institute, Ethiopia. Our main objective was to automate plant-disease identification using advanced deep learning approaches and image data. For the experiment, RGB image data were collected from the Bishoftu area. From the experimental results, the VGG19 model classified wheat disease with 99.38% accuracy.

Land Cover Change in the Blue Nile River Headwaters: Farmers’ Perceptions, Pressures, and Satellite-Based Mapping

The headwaters of the Blue Nile River in Ethiopia contain fragile mountain ecosystems and are highly susceptible to land degradation that impacts water quality and flow dynamics in a major transboundary river system. This study evaluates the status of land use/cover (LULC) change and key drivers of change over the past 31 years through a combination of satellite remote sensing and surveying of the local understanding of LULC patterns and drivers. Seven major LULC types (forest land, plantation forest, grazing land, agriculture land, bush and shrub land, bare land, and water bodies) from Landsat images of 1986, 1994, 2007, and 2017 were mapped. Agriculture and plantation forest land use/cover types increased by 21.4% and 368.8%, respectively, while other land use/cover types showed a decreasing trend: water body by 50.0%, bare land by 7.9%, grassland by 41.7%, forest by 28.9%, and bush and shrubland by 38.4%. Overall, 34.6% of the landscape experienced at least one LULC transition over the past 31 years, with 15.3% representing the net change and 19.3% representing the swap change. The percentage change in plantation forest land increased with an increasing altitude and slope gradient during the study period. The mapped LULC changes are consistent with the pressures reported by local residents. They are also consistent with root causes that include population growth, land tenure and common property rights, persistent poverty, weak enforcement of rules and low levels of extension services, a lack of public awareness, and poor infrastructure. Hence, the drivers for LULC should be controlled, and sustainable resources use is required; otherwise, these resources will soon be lost and will no longer be able to play their role in socioeconomic development and environmental sustainability.

Exploring Drivers of Forest Degradation and Fragmentation in Sudan: The Case of Erawashda Forest and its Surrounding Community

Sudan is a hot spot for forest degradation. Efforts to maintain what remains of its forests should be of the highest priority. However, precise information on its forests' current state is very limited. Therefore, in order to effectively intervene in support of existing resources, it is important to have a better understanding of processes taking place in the country and impacting those resources. The objectives of this study are to quantify the consequences of land use and land cover (LULC) changes on forest degradation and fragmentation and to analyze the anthropogenic factors causing it, taking Erawashda Forest, eastern Sudan, as an example. The study utilized a series of Landsat imageries, field surveys and interviews with informants to analyze the decrease in forest cover. The years between 1973 and 2015 saw a 16.9% and 5.4% increase in bare land and large-scale mechanized agriculture respectively. During the same period there was a 37% decrease in dense forest cover and a 20% increase in light forest cover. The trajectory analysis showed that all LULC categories are subjected to very rapid changes from one class to another throughout the period of the study and the most dynamic class is light forest cover. Computed fragmentation indices showed that large core is the dominant category. Key informants identified the main factors of degradation and fragmentation as the expansion of mechanized rain-fed agriculture, felling of trees and wood cutting, bad grazing activities, and construction of infrastructure. Information garnered from this study can provide a good basis for forest rehabilitation programs and can also be used for developing proper management plans that take into account the needs of the communities utilizing the forest.