Deep Learning for Land Cover Change Detection

AN ASSESSMENT OF SPATIAL VARIATION OF LAND SURFACE CHARACTERISTICS OF MINNA, NIGER STATE NIGERIA FOR SUSTAINABLE URBANIZATION USING GEOSPATIAL TECHNIQUES

Land cover change is a significant issue for environmental managers for sustainable management. Remote sensing techniques have been shown to have a high probability of recognizing land cover patterns and change detection due to periodic coverage, data integrity, and provision of data in a broad range of the electromagnetic spectrum. We evaluate the applicability of remote sensing techniques for land cover pattern recognition, as well as land cover change detection of the Hatiya Island, Bangladesh, and quantify land cover changes from 1977 to 1999. A supervised classification approach was used to classify Landsat Enhanced Thematic Mapper (ETM), Thematic Mapper (TM), and Multispectral Scanner (MSS) images into eight major land cover categories. We detected major land cover changes over the 22-year study period. During this period, marshy land, mud, mud with small grass, and bare soil had decreased by 85%, 46%, 44%, and 24%, respectively, while agricultural land, medium forest, forest, and settlement had positive changes of 26%, 45%, 363%, and 59%, respectively. The primary drivers of such landscape change were erosion and accretion processes, human pressure, and the reforestation and land reclamation programs of the Bangladesh Government.

Land use planners require up-to-date and spatially accurate time series land resources information and changing pattern for future management. As a result, assessing the status of land cover change due to population growth and arable expansion, land degradation and poor resource management, partial implementation of policy strategies, and poorly planned infrastructural development is essential. Thus, the objective of the study was to quantify the spatiotemporal dynamics of land use land cover change between 1995 and 2014 using 5 multi-temporal cloud-free Landsat Thematic Mapper images. The maximum likelihood (ML)-supervised classification technique was applied to create signature classes for significant land cover categories using means and variances of the training data to estimate the probability that a pixel is a member of a class. The final Bayesian ML classification resulted in 12 major land cover units, and the spatiotemporal change was quantified using post-classification and statistical change detection techniques. For a period of 20 years, there was a continuously increasing demand for arable areas, which can be represented by an exponential growth model. Excepting the year 2009, the built-up area has shown a steady increase due to population growth and its need for infrastructure development. There was nearly a constant trend for water bodies with a change in slope significantly less than +0.01%. The 2014 land cover change statistics revealed that the area was mainly covered by cultivated, wood, bush, shrub, grass, and forest land mapping units accounting nearly 63%, 12%, 8%, 6%, 4%, and 2% of the total, respectively. Land cover change with agro-climatic zones, soil types, and slope classes was common in most part of the area and the conversion of grazing land into plantation trees and closure area development were major changes in the past 20 years.

This paper analyzed land cover changes in Gazipur Sadar - an important urban fringe of expanding Dhaka City, Bangladesh, by leveraging remotely sensed imageries between 1973 and 2017. Landsat images of1973, 1991, 2006, and 2017 were classified using widely-preferred supervised classification method. Compared against ground-truth data, the reported classification accuracy ranges from 85% to 89%. Our classified land cover maps reveal that built-up areas in Gazipur Sadar increased by 312.9%, mostly replacing vegetation cover. An overall 199.7% decrease of vegetative covers highlights on the degree of urbanization process and increasing population pressure faced by Gazipur Sadar over the past decades. The rapid decrease of vegetative cover only 57 sq. km remains out of 344 sq. km throughout the region, including the Sal (Shorea robusta) forest and other floral species - invaluable resources for biodiversity and ecosystem health, should be taken as 'alarming' situation by the local authority responsible for promoting and managing sustainable development goals. In that light, this study emphasizes on the need for a critical assessment of future development initiatives in the Gazipur Sadar area and suggests for maintaining acceptable tradeoffs between development and environmental protection.

The relationship of land tenure, land use and land cover changes in Lake Victoria basin

A study coordinated by the MapBiomas project highlighted changes in land use and cover in the Caatinga in the period 1985-2020. To carry out the study, around 150,000 images from Landsat satellites were analyzed , with a resolution of 30 meters, available over a period of 35 years. Annual information was collected on twenty-five land use and land cover classes in the biome. In this post, we will highlight the main results of the study, which mapped the changes in the land cover of the Caatinga , in the last decades.

The high land use as area mining has resulted in changes in land cover and impacts the surrounding environment. In 2020, the Semarang City government implemented a Restrictions on Community Activities (RCA) policy to prevent the spread of the COVID-19 virus, indirectly limiting mining activities in the area of the Brown Canyon mine. This study aims to analyze the land cover change in the Brown Canyon mine area linked to the RCA policy. Assessment of land cover change is carried out by land cover classification on multitemporal Landsat imagery using Random Forest (RF) method. Based on the classification results, it was found that there was a change in mining land cover in Brown Canyon which increased by 3.713 Ha when the RCA policy was implemented from 46.305 Ha to 50.018 Ha. Likewise, after the implementation of RCA, there was an increase of 3.510 Ha from 50.018 Ha to 53.528 Ha. The accuracy of land cover classification before RCA was 90.12%. During RCA was 88.18%, and after RCA was 89.94%. Then, if related to the results of the interview data processing, the change in mining land cover that occurred was influenced by mining activities in the study area during the RCA period. So, it can also be said that RCA does not significantly influence mining activities in the Brown Canyon mining area. Several suggestions can be used for further research, such as using high-resolution satellite imagery and having mining area boundary data for each site.

The pace of change in land use and cover in Ethiopia depends on three main factors that cause pressure on agriculture land: resettlement programmes, population growth and increasing agricultural investments. Gambella is one of the regions of Ethiopia that attracts large-scale agricultural investments that extensively drive land use and cover changes in the region. The aim of this study is to examine the rate, extent and distribution of various land use and cover changes in Gambella Regional State, Ethiopia, from 1987 to 2017. The analysis is mainly based on Landsat 5 and Sentinel 2A satellite images and fieldwork. Two Landsat Thematic Mapper and a Sentinel 2A image were used for determining the maximum likelihood of land use/cover classification. The results show that farmland decreased by 26 km2 from 1987 to 2000; however, during the last two decades, agricultural land area increased by 599 km2, mainly at the cost of tropical grasslands and forests. We found that areas cultivated by smallholder farmers increased by 9.17% from 1987 to 2000. However, small-scale farm activities decreased by 7% from 2000 to 2017. Areas cultivated by large-scale state farms totalled 202 km2 in 1987; but by 2000, this large-scale state farming had been completely abandoned by the state, and as a result, its land use has decreased to zero. Despite this, in 2017 large-scale farming increased to 746 km2. In addition, Gambella National Park, which is the nation's largest national park and ecosystem, was also largely affected by Land Use and Land Cover changes. The conversion of savannah/tropical grasslands to agricultural farmland has caused varied and extensive environmental degradation to the park. The Land Use and Land Cover changes in the Gambella region are discussed on the basis of underlying socioeconomic factors.

Spatial analysis of land use and cover changes: Implications of green legacy initiative on climate action in Upper Awash Basin, Ethiopia

Understanding grassland habitat dynamics in space and time is crucial for evaluating the effectiveness of protection measures and developing sustainable management practices, specifically within the Natura 2000 network and in light of the European Biodiversity Strategy. Land cover maps, derived from remote sensing data, are essential for understanding long-term changes in vegetation cover and land use and assessing the impact of land use changes on grassland ecosystems. In this study, we conducted a 20-year land cover analysis of grassland landscapes in Umbria, Italy, using Random Forest classifications of Landsat data in Google Earth Engine. Our analysis was based on the years 2000, 2010, and 2020. We integrated harmonic modeling, Gray-Level Co-occurrence Matrix (GLCM) textural analysis, statistical image and gradient analysis, and other spectral and Digital Terrain Model (DTM)-derived indices to enhance the classification capabilities. The LandTrendr (LT) algorithm was used in GEE to collect ground control points in no-change areas automatically. We used a method based on Multilayer Perceptron-Artificial Neural Networks (MLP-ANNs) to forecast 2040 land cover. Our land cover classifications and the scenario model validation achieved an overall accuracy of over 90%. However, the classification of shrublands proved challenging due to their mixed composition and unique spatial patterns, resulting in lower accuracies. Feature importance analysis demonstrated the value of the enhanced map composition, and applying the LandTrendr algorithm simplified the diachronic land use and land cover (LULC) classification and change analysis by supporting automatic training data collection. Results support the interpretation of grassland dynamics in Umbria over the past two decades and identify areas affected by encroachment from shrubs, woody plants, or those with reduced green biomass. The forecasting method along with the selection of spatial drivers to predict land cover change, demonstrated high efficiency compared to other studies. A specific analysis was developed to identify areas where conservation measures related to the Natura 2000 network have been more or less effective in preserving grasslands. Overall, the research provides a scientific foundation for a methodology helpful in informing policy decisions and defining spatially explicit management strategies to enhance grassland conservation inside and outside Natura 2000 areas.

Land Use and Land Cover Change Detection in the Bhavani Basin of India through Remote Sensing Approach

Land cover change in the upstream area of the Jeneberang Watershed, South Sulawesi, has altered river hydrological dynamics and amplified the impacts of increasingly intense extreme rainfall associated with climate change, thereby elevating the risk of flash floods in downstream regions. This study aims to examine the relationship between upstream watershed degradation, trends in extreme rainfall, and the escalation of flash flood risk through an integrated spatial–temporal analysis. A quantitative approach was employed using secondary data, including multitemporal satellite imagery from 2003–2023, 20 years of daily rainfall records, documented flood events, and population data. The analysis involved land cover classification and change detection using GIS, trend testing of extreme rainfall with the Mann–Kendall method, estimation of runoff coefficients and peak discharge, and risk modeling based on the Hazard–Vulnerability–Exposure framework. The results indicate a 17.8% decline in forest cover in the upstream area, associated with a 19% increase in the runoff coefficient and a 24% rise in estimated peak discharge during high-intensity rainfall events. Maximum daily rainfall intensity also shows a statistically significant upward trend (p<0.05). Risk mapping reveals a 29% expansion of high-risk zones, particularly in densely populated downstream areas. These findings demonstrate that the interaction between land use change and intensifying extreme rainfall exacerbates watershed hydrological vulnerability, providing a scientific basis for upstream restoration policies and ecosystem-based climate change adaptation strategies in the Jeneberang Watershed

Land use land cover (LULC) change detection based on remote sensing data is an important source of information for various decision support systems for important to land conservation, sustainable development and management of water resources. The land use/ land cover mapping has been utilised for identifying the current land use pattern and changes occurred during 2000 and 2011 using satellite remote sensing technology and GIS tools. LANDSAT satellite imageries for the period 2000 and 2011 were used to prepare the land use/land cover (LULC) maps. Study area was characterised into nine classes. The classified images showed that Shallow water, Agriculture field with crops, open field without crop and Forest areas which have been decreased while Deep water, Marshy area, Orchard with other vegetation, Barren land and Built up area have increased during this period. This research highlights that remote sensing and GIS techniques could be effectively used for development of land use/land cover plan.

The development of improved satellite technology generates a huge amount of remote sensing data, these data play the crucial role in natural resource management. The land use and land cover (LULC) change intensely affects local environment, as well as the global environment. Therefore, the quantifiable knowledge about LULC changes occur in global scale is important to make effective planning for conservation and precise use of natural resources, that has motivated the scientists to develop the various land cover change detection techniques. In this paper, we have proposed neural network-based approach, i.e., focused time delay neural network (FTDNN)-based approach for land cover change detection, which is a time series prediction-based approach and detect the sudden change in the enhanced vegetation index (EVI) time series. The performance of the proposed method has been addressed by using quantitative and qualitative analysis techniques. For the quantitative evaluation, the proposed algorithm is applied to the standard synthetic data set, which are analogous to EVI time series data set. The performance result of the proposed method compares with the four previously existing data mining-based benchmark techniques. The analysis was shown that the FTDNN-based method significantly outperforms than other techniques. For qualitative analysis, the San Francisco Bay Area data set has been used, which comprises real EVI time series. The proposed FTDNN-based method is applied to the San Francisco Bay Area data set and observe the interesting land cover changes. These outcomes indicate the effectiveness of data mining techniques for the land cover change detection problem.

This study examines landscape changes in the context of China's national Grain for Green (GFG) policy, one of the world's largest "payment for environmental/ecosystem services" (PES) programs. We explored landscape structures and dynamics between 2000 and 2010 in Shaanxi Province, the Chinese province with the greatest amount of cropland conversion and reforestation in recent decades. We used Landsat Thematic Mapper (TM)-derived data and landscape metrics for six land cover classes to determine (1) the major land cover changes during enforcement of the policy, (2) the spatial and temporal variations in these changes, and (3) the effects of land cover changes on landscape structure and dynamics. The results suggested that provincial-level land cover changes modestly reflected the goals of the GFG. Over the 10-year study period, the forest and grassland coverages expanded from 95,737.9 to 97,017.4km(2) and from 37,235.9 to 40,613.1km(2), respectively, while the cropland coverage decreased from 59,222.8 to 54,007.6km(2). The conversion direction differed regionally: the targeted croplands in Shanbei, namely, types III and IV, were mainly transformed into grassland while those in Shannan were mainly transformed into forestland. Reforestation was associated with increased inter-landscape aggregation and connection. Despite this large-scale reforestation trend, we found notable and significant differences in the land cover changes at the subprovincial level.