Hybrid classification of Landsat data and GIS for land use/cover change analysis of the Bindura district, Zimbabwe

Kamusoko, Courage; Aniya, Masamu

doi:10.1080/01431160802244268

Cited by 48 publications

(38 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The problem was solved using a hybrid-supervised/unsupervised classification that was analyzed using Geographical Information System (GIS) algorithms that produced neighborhood and matricial representations [33].…”

Section: Hybrid-supervised Classificationmentioning

confidence: 99%

A Quantitative Approach for Analyzing the Relationship between Urban Heat Islands and Land Cover

2012

View full text Add to dashboard Cite

With more than 80% of Brazilians living in cities, urbanization has had an important impact on climatic variations. São José dos Campos is located in a region experiencing rapid urbanization, which has produced a remarkable Urban Heat Island (UHI) effect. This effect influences the climate, environment and socio-economic development on a regional scale. In this study, the brightness temperatures and land cover types from Landsat TM images of São José dos Campos from 1986, 2001 and 2010 were analyzed for the spatial distribution of changes in temperature and land cover. A quantitative approach was used to explore the relationships among temperature, land cover areas and several indices, including the Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI) and Normalized Difference Built-up Index (NDBI). The results showed that urban and bare areas correlated positively with high temperatures. Conversely, areas covered in vegetation and water correlated positively with low temperatures. The indices showed that correlations between the NDVI and NDWI and temperature were low (<0.5); however, a moderate correlation was found between the NDBI and temperature.

show abstract

Section: Hybrid-supervised Classificationmentioning

confidence: 99%

A Quantitative Approach for Analyzing the Relationship between Urban Heat Islands and Land Cover

2012

View full text Add to dashboard Cite

show abstract

“…Therefore, remote sensing of human activities in Zimbabwe can provide a more effective mirror for the economic decline. A few studies of Zimbabwe on land cover change mapping [45] and human settlement detection [46] seem to have stronger link to the socioeconomic aspects. However, these works made use of medium or high resolution remote sensing imagery, which is too costly when applied in national scale.…”

Section: Discussionmentioning

confidence: 99%

Detecting Zimbabwe’s Decadal Economic Decline Using Nighttime Light Imagery

Liu

Chen

2013

Remote Sensing

View full text Add to dashboard Cite

Zimbabwe's economy declined between 2000 and 2009. This study detects the economic decline in different regions of Zimbabwe using nighttime light imagery from the Defense Meteorological Satellite Program's Operational Linescan System (DMSP-OLS). We found a good correlation (coefficient = 0.7361) between Zimbabwe's total nighttime light (TNL) and Gross Domestic Product (GDP) for the period 1992 to 2009. Therefore, TNL was used as an indicator of regional economic conditions in Zimbabwe. Nighttime light imagery from 2000 and 2008 was compared at both national and regional scales for four types of regions. At the national scale, we found that nighttime light in more than half of the lit area decreased between 2000 and 2008. Moreover, within the four region types (inland mining towns, inland agricultural towns, border towns and cities) we determined that the mining and agricultural sectors experienced the most severe economic decline. Some of these findings were validated by economic survey data, proving that the nighttime light data is a potential data source for detecting the economic decline in Zimbabwe.

show abstract

“…One land cover study which attempts to map cropping areas of central Ethiopia achieved overall accuracy of 55%-74% for its agricultural classes that were differentiated based on intensity of cropping by supplementing wide area use of Landsat TM data with limited area use of 1-m resolution IKONOS imagery [17]. In a single district of Zimbabwe, an area of about 2000 km 2 , land cover mapping through a combined method of unsupervised and supervised classification schemes achieved 85% accuracy including within agriculture but much of that is large-scale commercial agriculture [18]. A dense time stack of imagery for a single year coupled with phenological curves fed into a decision tree was important in discerning irrigated from rainfed agriculture in West Africa, but there was still difficulty in separating rainfed agriculture from natural vegetation in the heterogeneous smallholder landscape [19].…”

Section: Introductionmentioning

confidence: 99%

Land Cover Classification in Complex and Fragmented Agricultural Landscapes of the Ethiopian Highlands

et al. 2016

View full text Add to dashboard Cite

Ethiopia is a largely agrarian country with nearly 85% of its employment coming from agriculture. Nevertheless, it is not known how much land is under cultivation. Mapping land cover at finer resolution and global scales has been particularly difficult in Ethiopia. The study area falls in a region of high mapping complexity with environmental challenges which require higher quality maps. Here, remote sensing is used to classify a large area of the central and northwestern highlands into eight broad land cover classes that comprise agriculture, grassland, woodland/shrub, forest, bare ground, urban/impervious surfaces, water, and seasonal water/marsh areas. We use data from Landsat spectral bands from 2000 to 2011, the Normalized Difference Vegetation Index (NDVI) and its temporal mean and variance, together with a digital elevation model, all at 30-m spatial resolution, as inputs to a supervised classifier. A Support Vector Machines algorithm (SVM) was chosen to deal with the size, variability and non-parametric nature of these data stacks. In post-processing, an image segmentation algorithm with a minimum mapping unit of about 0.5 hectares was used to convert per pixel classification results into an object based final map. Although the reliability of the map is modest, its overall accuracy is 55%-encouraging results for the accuracy of agricultural uses at 85% suggest that these methods do offer great utility. Confusion among grassland, woodland and barren categories reflects the difficulty of classifying savannah landscapes, especially in east central Africa with monsoonal-driven rainfall patterns where the ground is obstructed by clouds for significant periods of time. Our analysis also points out the need for high quality reference data. Further, topographic analysis of the agriculture class suggests there is a significant amount of sloping land under cultivation. These results are important for future research and environmental monitoring in agricultural land use, soil erosion, and crop modeling of the Abay basin.

show abstract

Hybrid classification of Landsat data and GIS for land use/cover change analysis of the Bindura district, Zimbabwe

Cited by 48 publications

References 34 publications

A Quantitative Approach for Analyzing the Relationship between Urban Heat Islands and Land Cover

A Quantitative Approach for Analyzing the Relationship between Urban Heat Islands and Land Cover

Detecting Zimbabwe’s Decadal Economic Decline Using Nighttime Light Imagery

Land Cover Classification in Complex and Fragmented Agricultural Landscapes of the Ethiopian Highlands

Contact Info

Product

Resources

About