Spatio-temporal Change Detection Research Articles

The change detection in coastal settlements using image processing techniques: a case study of Korfez.

Coastal areas all over the world are usually exposed to intensive change and transformation processes resulting in a variety of natural, physical, and socio-economic problems. Körfez province, located along the İzmit Bay of Marmara Sea, Turkey, has been one of these coastal areas that has become a major point for industrial facilities and highly populated urbanized area since 1960s. Therefore, the analysis of the spatial changes in the land use patterns of the province has a critical role in the success of the physical planning processes and the protection of the coastal areas. In order to highlight this critical role, temporal change detection analysis for Körfez province covering a 6-year period and 5 land use classes was made using 2009 and 2015 SPOT imagery and thematic maps. Reclassified CORINE data, development plans, and land survey results were benefited for the supervised classification of the images. Four hundred eighty control points for each year were used to achieve a strong accuracy tested by Kappa coefficient. The spatio-temporal change detection results revealed a 22.5% and 2.3% decrease in agricultural lands and sea areas respectively, while there was an increase of 16.6% in forest-green areas, 6.4% in settlement areas, and 74.1% in lake areas. The results are believed to be significant input data to facilitate coastal and physical development planning over the area, and thus make sustainable land use decisions to protect the delicate landscape and coastal characteristics, while providing a sound risk management plan.

Dust storm index anomaly for sand-dust events monitoring in western Iran and its association with the NDVI and LST anomalies

Sand-dust events (SDE) are an increasing concern in many arid and semi-arid regions of the world, which have severely damaged air quality and human health in recent years. This study was conducted to monitor the SDE in western Iran using the dust storm index anomaly (DSIA) during 2000-2018. The spatio-temporal change detection and statistical analysis were used to understand the impacts of normalized difference vegetation cover anomaly (NDVIA) and land surface temperature anomaly (LSTA) on the SDE activities. The area has suffered from the highest dust pollution in 2004, 2009, and 2012 (DSIA>+40) while it experienced the lowest dust pollution in 2002 and 2017 (DSIA<-40). Approximately 48% of western Iran experienced decreasing changes and 52% of the total area experienced increasing changes in dust pollution during 2010-2018 compared to the previous years. Incremental changes in NDVIA and LSTA were observed in 73.2% and 7.5% of the study area while their decreasing changes were observed in 26.8% and 92.5% of the total area, respectively. Spatially, regions affected by the increase in dust pollution are mainly distributed in the eastern and southern regions of the study area. Significant effects of changes in anomalies of both terrestrial parameters on DSIA were observed throughout the study period ((RLSTA-DSIA= +0.52; RNDVIA-DSIA= -0.41); P<0.05). It was also found that spatial correlation between LSTA and DSIA, as well as NDVIA and DSIA in many parts of the study area, was significant at the 95% confidence level (|R| > 0.45). These findings can be useful for decision-makers to assess the risks of dust pollution and reduce its negative consequences in western Iran.

A simple approach for monitoring vegetation change using time series remote sensing analysis: A case study from the Thathe Vondo Area in Limpopo Province, South Africa

This study presents a simple approach of spatiotemporal change detection of vegetation cover based on analysis of time series remotely sensed images. The study was carried out at Thathe Vondo Area, which is characterised by episodic variation of vegetation gain and loss. This variation is attributable to timber and tea plantations and their production cycles, which periodically result in either vegetation gain or loss. The approach presented here was implemented on two ASTER images acquired in 2007 and 2017. It involved the combined use of band combination, unsupervised image classification and Normalised Difference Vegetation Index (NDVI) techniques. True colour composite (TCC) images for 2007 and 2017 were created from combination of bands 1, 2 and 3 in red, blue and green, respectively. The difference image of the TCC images was then generated to show the inconsistencies of vegetation cover between 2007 and 2017. For analytical simplicity and interpretability, the difference image was subjected to ISODATA unsupervised classification, which clustered pixels in the difference image into eight classes. Two ISODATA derived classes were interpreted as vegetation gain and one as vegetation loss. These classes were confirmed as regions of vegetation gain and loss by NDVI values of 2007 and 2017. In addition, the polygons of vegetation gain and loss regions were created and superimposed over the TCC images to further demonstrate the spatiotemporal vegetation change in the area. The vegetation change statistics show vegetation gain and loss of 10.62% and 2.03%, respectively, implying a vegetation gain of 8.59% over the selected decade.Significance:&#x0D; &#x0D; Vegetation change detection is essential in environmental monitoring and management of an area. This study presents a simple approach for assessing vegetation change over time. The approach involveschange detection through the difference of spectral values of vegetation pixels of time series remotelysensed images.&#x0D;

A Spatiotemporal Change Detection Method for Monitoring Pine Wilt Disease in a Complex Landscape Using High-Resolution Remote Sensing Imagery

Using high-resolution remote sensing data to identify infected trees is an important method for controlling pine wilt disease (PWD). Currently, single-date image classification methods are widely used for PWD detection in pure stands of pine. However, they often yield false detections caused by deciduous trees, brown herbaceous, and sparsely vegetated regions in complex landscapes, resulting in low user accuracies. Due to the limitations on the bands of the high-resolution imagery, it is difficult to distinguish wilted pine trees from such easily confused objects when only using the optical spectral characteristics. This paper proposes a spatiotemporal change detection method to reduce false detections in tree-scale PWD monitoring under a complex landscape. The framework consisted of three parts, which represent the capture of spectral, temporal, and spatial features: (1) the Normalized Green–Red Difference Index (NGRDI) was calculated as a descriptor of canopy greenness; (2) two NGRDI images with similar dates in adjacent years were contrasted to obtain a bitemporal change index that represents the temporal behaviors of typical cover types; and (3) a spatial enhancement was performed on the change index using a convolution kernel matching the spatial patterns of PWD. Finally, a set of criteria based on the above features were established to extract the wilted pine trees. The results showed that the proposed method effectively distinguishes wilted pine trees from other easily confused objects. Compared with single-date image classification, the proposed method significantly improved user’s accuracy (81.2% vs. 67.7%) while maintaining the same level of producer’s accuracy (84.7% vs. 82.6%).

Spatiotemporal change detection of ecological quality and the associated affecting factors in Dongting Lake Basin, based on RSEI

Maintaining optimal ecological security in Dongting Lake Basin is of great significance to national projects of Yangtze River Economic Belt Construction and Yangtze River Protection. Ecological quality and the potential associated affecting factors are important contents of ecological security in Dongting Lake Basin. In this research, remote sensing ecological index (RSEI) were used to analyze the temporal and spatial variation in the ecological qualities in Dongting Lake Basin during 2001–2019 and determine the potential associated affecting factors. Results showed that the overall ecological quality fluctuated during 2001–2019. The change intensities among different RSEI levels were relative low (absolute change values of 1 and 2) and mainly changed among fair, moderate and good levels. Land use/cover, climate (average annual rainfall) and human interferences (GDP) were the associated potential factors affecting the ecological quality in Dongting Lake Basin. Among these factors, areas and qualities of woody savannas, savannas, mixed forests, and cropland/natural vegetation mosaics were the most important factors affecting the ecological quality (RSEI). While other land use/cover (i.e., Croplands, Evergreen Needleleaf Forests, Parmanent Wetlands, Grasslands), climate (average annual rainfall) and human interferences (GDP) also had contributions to the ecological quality. Specifically, such four land use/cover, average annual rainfall were positively but GDP negatively correlated with the ecological quality. In conclusion, changes in the area and quality of different land use types might explain most of the ecological quality variations in Dongting Lake Basin. These findings will provide significant information for managers to make more targeted ecological restoration efforts in Dongting Lake Basin.

Spatiotemporal monitoring and change detection of vegetation cover for drought management in the Middle East

The Middle East (ME), as an arid and semi-arid region, is prone to environmental risks and stresses, such as drought are inseparable phenomena of the region. In this study, an approach for identifying sustained vegetation cover (SVC) is suggested to identify the connection between SVC and drought. Normalized difference vegetation index (NDVI) and land surface temperature (LST) were used to filter zones of rich vegetation cover from poorly vegetated or non-vegetated regions of the ME. The change detection of vegetation cover was computed by the NDVI differencing technique, and the vegetation condition index (VCI) and normalized vegetation supply water index (NVSWI) were used to derive drought indices. The standardized precipitation index (SPI) and rainfall anomaly index (RAI) were used to monitor the intensity of meteorological drought events. A comparison of the estimates of vegetation change, remote sensing-based VCI, and meteorological drought indices revealed that the highest SVC is concurrent with the occurrence of drought. Moreover, it was found that the most severe meteorological drought and VCL-based drought condition occurred in 2008 and that the highest percentage of SVC was also obtained for this year. The results suggest the possibility of using the SVC instead of other spectral indices, such as the NDVI, VCI, NVSWI, and NVSWI, for the superior assessment and detection of environmental stresses such as drought.

Spatio-Temporal Change Detection and Its Impact on the Waterbodies by Monitoring LU/LC Dynamics - A Case Study from Holy City of Ratanpur, Chhattisgarh, India

Spatio-Temporal Change Detection and Its Impact on the Waterbodies by Monitoring LU/LC Dynamics - A Case Study from Holy City of Ratanpur, Chhattisgarh, India

Hybrid modelling approach for water body change detection at Chalan Beel area in northern Bangladesh

Water is a strategic resource for both socio-economic development and human life. The current study has been carried out for spatio-temporal change detection of surface water bodies during winter period using hybrid modelling approach. The study area has fallen in the northern part of Bangladesh and is locally called Chalan Beel with 5 million of in habitants, a prominent intensive crop production, surface and groundwater irrigation, high evapotranspiration, and water scarcity. For the detection of water body changes, satellite images of 1999 and 2011 were used, and the following image fusion techniques were applied: (a) Gram-Schmidt (GS), (b) modified intensity hue saturation (IHS), (c) high-pass filter (HPF), and (d) wavelet. Landsat 7/ETM + panchromatic (PAN) band of 15 m × 15 m resolution in 1999 and Landsat 5/TM multispectral (MS) bands of 30 m × 30 m resolution in 2011 were allied each other to generate high-resolution image that contains information of two different years. The fused images were classified to extract the water bodies using four classification methods: (a) artificial neural network (ANN), (b) support vector machine (SVM) and (c) maximum likelihood (ML). To analyze the quality of the fused images, statistical calculation (quantitatively) and Laplacian edge detection (qualitatively) were used. To validate the fused image classification results, the multispectral images from 1999 and 2011 were again individually classified using principal component analysis (PCA), normalized difference water index (NDWI), and image differencing (ID) processes and compared with the previous classification. Surprisingly, the results showed that two-third of the areas dried up in 10 years.

Spatiotemporal Change Detection of the Linden Forests in Bursa, Turkey

Nonwood forest products potentially provide many economic, social and environmental benefits in Turkey. Increasing public demand for nonwood forest products has led to the development of spatial planning and updating of existing plans. In order to ensure the sustainable management of nonwood forest products, their trends and spatial distributions by time can be estimated by using land use/land cover change detection approach. The Linden is one of the most important nonwood forest products in Turkey and the most widespread distribution of linden is located in the province of Bursa. In this study, it was aimed to determine the spatiotemporal changes of one of the world's largest linden forests in Yeniköy Forestry Enterprise Chief within the border of Bursa Forestry Regional Directorate. Change detection analysis was applied to Landsat 5 TM image and Landsat 8 OLI/TIRS image captured in August 2008 and in July 2017, respectively. The spatiotemporal change detection was implemented on these two images by using various digital image processing techniques (pre-processing, classification, post-processing, and change detection) through ERDAS Imagine 2015, ArcGIS 10.5, and ENVI 5.3 program. The supervised classification, applied on both images using ERDAS Imagine 2015 program, revealed that there were six significant land use/land cover types in the study area; linden, other deciduous trees, wetlands, swamp, sand, and other lands (settlements, agriculture, open areas). The results indicated that there was increase in the areas of wetlands, sand, and other lands, while the area of linden forest, other deciduous trees, and swamp decreased from 2008 to 2017. According to the accuracy assessment results, the classification processes applied on 2008 and 2017 images provided overall accuracy of 84.38% and 82.81%, respectively. It is determined that some of the linden forests have been converted into residential areas and farmlands to grow crops.

Detection of Spatiotemporal Extreme Changes in Atmospheric CO2 Concentration Based on Satellite Observations

Atmospheric CO2 concentrations are sensitive to the effects of climate extremes on carbon sources and sinks of the land biosphere. Therefore, extreme changes of atmospheric CO2 can be used to identify anomalous sources and sinks of carbon. In this study, we develop a spatiotemporal extreme change detection method for atmospheric CO2 concentrations using column-averaged CO2 dry air mole fraction (XCO2) retrieved from the Greenhouse gases Observing SATellite (GOSAT) from 1 June 2009 to 31 May 2016. For extreme events identified, we attributed the main drivers using surface environmental parameters, including surface skin temperature, self-calibrating Palmer drought severity index, burned area, and gross primary production (GPP). We also tested the sensitivity of XCO2 response to changing surface CO2 fluxes using model simulations and Goddard Earth Observing System (GEOS)-Chem atmospheric transport. Several extreme high XCO2 events are detected around mid-2010 over Eurasia and in early 2016 in the tropics. The magnitudes of extreme XCO2 increases are around 1.5–1.8 ppm in the Northern Hemisphere and 1.2–1.4 ppm in Southern Hemisphere. The spatiotemporal pattern of detected high XCO2 events are similar to patterns of local surface environmental parameter extremes. The extreme high XCO2 events often occurred during periods of increased temperature, severe drought, increased wildfire or reduced GPP. Our sensitivity tests show that the magnitude of detectable anomalies varies with location, for example 25% or larger anomalies in local CO2 emission fluxes are detectable in tropical forest, whereas anomalies must be half again as large in mid-latitudes (~37.5%). In conclusion, we present a method for extreme high XCO2 detection, and large changes in land CO2 fluxes. This provides another tool to monitor large-scale changes in the land carbon sink and potential feedbacks on the climate system.

SPATIOTEMPORAL CHANGE DETECTION USING LANDSAT IMAGERY: THE CASE STUDY OF KARACABEY FLOODED FOREST, BURSA, TURKEY

Abstract. This short paper aims to detect spatiotemporal detection of land use/land cover change within Karacabey Flooded Forest region. Change detection analysis applied to Landsat 5 TM images representing July 2000 and a Landsat 8 OLI representing June 2017. Various image processing tools were implemented using ERDAS 9.2, ArcGIS 10.4.1, and ENVI programs to conduct spatiotemporal change detection over these two images such as band selection, corrections, subset, classification, recoding, accuracy assessment, and change detection analysis. Image classification revealed that there are five significant land use/land cover types, including forest, flooded forest, swamp, water, and other lands (i.e. agriculture, sand, roads, settlement, and open areas). The results indicated that there was increase in flooded forest, water, and other lands, while the cover of forest and swamp decreased.

Exploring geospatial techniques for spatiotemporal change detection in land cover dynamics along Soan River, Pakistan.

Classification of land cover dynamics via satellite imagery has played indispensible services in developing effective management strategies for evaluation and management of water resources. The present study employed geospatial techniques, i.e., integrated GIS and remote sensing for effectual land change study. Hybrid classification approach was applied using ERDAS Imagine 11 to detect changes in land cover dynamics using satellite imagery of Landsat 4, 5 TM, Landsat 7 ETM, and Landsat 8 OLI for the years of 1992, 2002, and 2015, respectively. The study area was classified into four categories, i.e., vegetation, water body, barren, and urban area. Resultant maps, overlay maps, and post classification comparison maps were produced using ArcGIS 10.2 indicated remarkable shrinkage of water body up to 58.81%, reduction in vegetation area 53.24%, and increase in urban and barren area to 49.04 and 137.32%, respectively. The significant changes in land cover dynamics of Soan River are posing threats to its survival. Therefore, proper management, policies, and development of land use inventory are needs of the hour for saving Soan River.

Assessment of the Temporal Variations of Surface Water Bodies in and around Chennai using Landsat Imagery

Urban India is witnessing a rapid growth that has an impact on the fate of water bodies. Chennai, one of the fastest growing metropolitan cities in India, is not an exception to this urbanization process. Chennai's precious water resources are under severe stress. Further, the recent, 100-year flood disaster that occurred in November-December 2015 over Chennai has had tragic consequences on its population and has brought back the focus on its water bodies. Remote sensing combined with GIS techniques enable accurate spatiotemporal change detection of natural resources. Landsat and multispectral imageries provide reliable and accurate data for the detection of changes in the areal extents of surface water bodies. Spatiotemporal change analyses on the surface water bodies in Chennai and its surrounding areas were conducted through water extraction techniques by using indexes, such as WRI, NDWI and MNDWI using GIS software. The changes in the surface water bodies were estimated by analyzing and using Landsat images for the pre- and post-monsoon periods of the years1977-78, 1988-89, 1997-98, 2006-07 and 2015-16. The changes and their variations in the indexes and the interpretation of these changes are discussed. NDWI is most suitable for extracting surface water bodies. WRI and MNDWI can be used for the extraction of surface water bodies only from those satellite imageries that have the MIR band. However, MNDWI is suitable for inundated areas within a largely urban-covered region. Hence, urban planners can utilize these results for better urban planning and flood-disaster management.

Spatio-temporal variability of temperature and potential evapotranspiration over India

Worldwide, major changes in the climate are expected due to global warming, which leads to temperature variations. To assess the climate change impact on the hydrological cycle, a spatio-temporal change detection study of potential evapotranspiration (PET) along with maximum and minimum temperatures (Tmax and Tmin) over India have been performed for the second half of the 20th century (1950–2005) both at monthly and seasonal scale. From the observed monthly climatology of PET over India, high values of PET are envisioned during the months of March, April, May and June. Temperature is one of the significant factors in explaining changes in PET. Hence seasonal correlations of PET with Tmax and Tmin were analyzed using Spearman rank correlation. Correlation of PET with Tmax was found to be higher compared to that with Tmin. Seasonal variability of trend at each grid point over India was studied for Tmax, Tmin and PET separately. Trend Free Pre-Whitening and Modified Mann Kendall approaches, which consider the effect of serial correlation, were employed for the trend detection analysis. A significant trend was observed in Tmin compared to Tmax and PET. Significant upward trends in Tmax, Tmin and PET were observed over most of the grid points in the interior peninsular region.

Spatio-temporal change detection from multidimensional arrays: Detecting deforestation from MODIS time series

Growing availability of long-term satellite imagery enables change modeling with advanced spatio-temporal statistical methods. Multidimensional arrays naturally match the structure of spatio-temporal satellite data and can provide a clean modeling process for complex spatio-temporal analysis over large datasets. Our study case illustrates the detection of breakpoints in MODIS imagery time series for land cover change in the Brazilian Amazon using the BFAST (Breaks For Additive Season and Trend) change detection framework. BFAST includes an Empirical Fluctuation Process (EFP) to alarm the change and a change point time locating process. We extend the EFP to account for the spatial autocorrelation between spatial neighbors and assess the effects of spatial correlation when applying BFAST on satellite image time series. In addition, we evaluate how sensitive EFP is to the assumption that its time series residuals are temporally uncorrelated, by modeling it as an autoregressive process. We use arrays as a unified data structure for the modeling process, R to execute the analysis, and an array database management system to scale computation. Our results point to BFAST as a robust approach against mild temporal and spatial correlation, to the use of arrays to ease the modeling process of spatio-temporal change, and towards communicable and scalable analysis.

Spatiotemporal Change Detection Analysis of Turkish Lake Water Surface Area in Response to Anthropogenic Ecosystem Disturbances Using Long-Term Landsat TM/ETM+ Data

The provision of diverse ecosystem goods and services by lakes is vital to ecosystem health and economic well-being of nations or regions. Securing ecologically safe lake water quality and quantity through sustainable uses and management practices concerns both present and future generations. The present study quantifies long-term impacts of human-induced disturbances including climate change on water surface areas of the 18 largest Turkish lakes. Spatiotemporal change detection analysis was carried out using long-term Landsat time series data between 1973 and 2014 with the aid of geographical information systems (GIS). Supervised and unsupervised classification techniques were combined to temporally differentiate and spatially delineate lake water surface areas using ancillary data. Over the period of about 40 years, lake surface area decreased for 15 lakes at a mean annual rate of 0.96 km2 but increased for three lakes at a mean annual rate of 0.17 km2. These spatiotemporal changes may be attributed to such human-induced pressures as drought, sectoral water uses/withdrawals, draining, and landfilling. These changes in turn lead to losses of or damages to both marketable and non-marketable ecosystem benefits that the lakes provide with humans at the local-to-regional spatial scales in the long-to-short-term temporal scales. The integration of remote sensing and GIS techniques adopted in this study allows for dynamic monitoring of not only lake water quality and quantity but also other natural resources, thus facilitating a timely and effective development of preventive and mitigative measures.

Long-Term Stationary Object Detection Based on Spatio-Temporal Change Detection

We present a block-wise approach to detect stationary objects based on spatio-temporal change detection. First, block candidates are extracted by filtering out consecutive blocks containing moving objects. Then, an online clustering approach groups similar blocks at each spatial location over time via statistical variation of pixel ratios. The stability changes are identified by analyzing the relationships between the most repeated clusters at regular sampling instants. Finally, stationary objects are detected as those stability changes that exceed an alarm time and have not been visualized before. Unlike previous approaches making use of Background Subtraction, the proposed approach does not require foreground segmentation and provides robustness to illumination changes, crowds and intermittent object motion. The experiments over an heterogeneous dataset demonstrate the ability of the proposed approach for short- and long-term operation while overcoming challenging issues.

Rapid detection of new and expanding human settlements in the Limpopo province of South Africa using a spatio-temporal change detection method

Recent development has identified the benefits of using hyper-temporal satellite time series data for land cover change detection and classification in South Africa. In particular, the monitoring of human settlement expansion in the Limpopo province is of relevance as it is the one of the most pervasive forms of land-cover change in this province which covers an area of roughly 125000km2. In this paper, a spatio-temporal autocorrelation change detection (STACD) method is developed to improve the performance of a pixel based temporal Autocorrelation change detection (TACD) method previously proposed. The objective is to apply the algorithm to large areas to detect the conversion of natural vegetation to settlement which is then validated by an operator using additional data (such as high resolution imagery). Importantly, as the objective of the method is to indicate areas of potential change to operators for further analysis, a low false alarm rate is required while achieving an acceptable probability of detection. Results indicate that detection accuracies of 70% of new settlement instances are achievable at a false alarm rate of less than 1% with the STACD method, an improvement of up to 17% compared to the original TACD formulation.

Ice calving and deformation from Antarctic Ice margins using RISAT-1 circular polarization SAR data

Abstract. In the present study, quantification of spatial and temporal changes has been carried out between Indian Antarctic Research station Bharati and Amery ice shelf by monitoring the ice margins using RISAT-1 Synthetic Aperture Radar (SAR) data. Spatio-temporal change detection was carried out by comparing the feature's geographic locations from geometrically rectified SAR data from RISAT-1 (Dec. 2013), Radarsat-2 (Feb. 2013), and Antarctic Mapping Mission products of Radarsat-1 (1997 &amp;amp; 2000). We report large scale disintegrations at two prominent glacier tongues namely Polar Record Glacier (PRG) and Polar Times Glacier(PTG). The results are verified against in-situ ground observations made during Summer period of 33rd ISEA (Dec. 2013–Feb. 2014) and MODIS images from NSIDC archive. Polar Record Glacier Tongue (PRGT) was drastically deformed by 135.8 km2 and Polar Times Glacier Tongue (PTGT) was partly calved by ~195.6 km2 and moved away by ~23 km especially between February and December 2013.

Examining Spatio-Temporal Change Detection in the Indus River Delta with the Help of Satellite Data

The morphology of a river thalweg in a deltaic environment is continuously reshaped by the interactive balancing of the fluvial and marine hydrodynamic processes. Fluvial flow parameters such as volume and flow velocity are favorable to increase the width of thalweg and develop a braided pattern in river course within a delta region. The present study utilized historical satellite images to show that as result of the development of the world largest water divergent networks, the Indus River discharge and sediments load discharge into the Indus delta have been enormously depleted in the last 150 years. Satellite images revealed significant and successive narrowing of the thalweg and distinct widening of the course of the Indus River near the delta. Based on the model results, we show that the style of the rapid morphological changes demonstrates seaward widening and the landward narrowing of the Indus river course and its thalweg. Our results indicate that anthropogenic diversions of the flow in the upstream region of the Indus River have resulted in the devastating domination of marine hydrodynamic processes over the weakened and destabilized natural fluvial processes in the delta region.