Multi-temporal Images Research Articles

Inventory and Spatiotemporal Patterns of Glacial Lakes in the HKH-TMHA Region from 1990 to 2020

The Himalayan, Karakoram, and Hindu Kush (HKH-TMHA) are the three main mountain ranges in the high-mountain Asia region, covering the China–Pakistan Economic Corridor (CPEC). In this study, we identified glacial lakes in the HKH-TMHA region based on multitemporal Landsat images taken from 1990 to 2020. We analyzed the spatial distribution and evolution of glacial lakes in the HKH-TMHA region from the perspective of their elevation, size, and terrain aspect; then, we described their temporal changes. The results showed that approximately 84.56% of the glacial lakes (84.1% of the total lake area) were located at elevations between 4000 m and 5500 m, and glacial lakes with areas ranging from 0.01–0.5 km2 accounted for approximately 95.21% of the number and 63.01% of the total area of glacial lakes. The number (38.64%) and area (58.83%) of south-facing glacial lakes were largest in HKH-TMHA and expanded significantly over time. There were 5835 (664.84 ± 89.72 km2) glacial lakes in 1990; from 1990 to 2020, the number of glacial lakes in the HKH-TMHA region increased by 5974 (408.93 km2) in total; and the annual average increase in the area of glacial lakes reached 13.63 km2 (11.15%). In 2020, the total number of glacial lake reached to 9673 (899.66 ± 120.63 km2). In addition, most glacial lakes were located in the Eastern Himalayan, China, and the Indus Basin. Based on the precipitation and temperature analyses performed in our study area, we found inconsistent climate characteristics and changes in the three mountain ranges. In general, the daily precipitation (temperature) increased by 1.0766 mm (1.0311 °C), 0.8544 mm (0.8346 °C), and 0.8245 mm (−0.1042 °C) on the yearly, summer, and winter scales, respectively. Glacial melting and climate change are common contributors to glacial lake expansion. The investigation of glacial lakes in this region can provide basic supporting data for research on glacial lake-related disasters, land cover, and climate change in the high-mountain Asia region.

Detection of bare soils in sugarcane areas by temporal satellite images: A monitoring technique for soil security

Bare soil triggers several undesirable processes for its quality and remote sensing can be a powerful tool to monitoring its occurrence. This work aims to apply multi-temporal satellite image techniques to detect bare soil areas under sugarcane cultivation and relate with soil security. The study was carried out in an area of 2,574 km² located in Brazil. The MapBiomas land use and cover collection was used to know the sugarcane area changes from 1985 to 2019. A collection of Landsat images over 35 years (1985 to 2019) were used to create Synthetic Soil Images (SYSIs) and the Bare Soil Frequency Images (BSF) of the area. SYSIs were generated annually, in the rainy and dry season. BSFs was generated in the total period and every five years by dry and rainy season. Thus, the land use changes and bare soil occurrence were compared to categorical maps of soil types, surface clay classes and slope, and also with economic, social and political changes in the period. In general, the bare soil increased from 1985 to 2006, and began to decline thereafter because of “Agro-environmental Protocol’ that anticipated the end of pre-harvest burning in sugarcane crop. BSF in the rainy season decreased over the period motivated by knowledge of farmers and changes in management. Despite this, many prone to erosion soils classes (Arenosols, Lixisols/Acrisols) remain under conventional tillage in the rainy season. We concluded that the use of multi-temporal satellite images is an important approach to monitoring soil management contributing to soil security.

Pixel- and Object-Based ensemble learning for forest burn severity using USGS FIREMON and Mediterranean condition dNBRs in Aegean ecosystem (Turkey)

Forest fires cause aerosol emissions and biomass burning that pose major threats to the ozone layer. The precise estimation of burned area with the degree of burn severity plays a critical role to investigate the impacts of fire on forests. Burn severity analysis using remotely sensed data has become popular in the last decade for post-fire detection, management and mitigation studies. In this study, performances of three ensemble learning algorithms, namely, random forest (RF), rotation forest (RotFor), and canonical correlation forest (CCF) were analyzed on burn severity mapping in terms of pixel-and object-based image analyses applying standard accuracy metrics and McNemar’s statistical test. The classification procedures were applied to two fire-affected areas located in Izmir province, Turkey using multitemporal (pre-and post-fire) Sentinel-2A images. The results showed that the CCF classifier outperformed the RF and RotFor classifiers for both pixel-and object-based classifications in that classification accuracies varied by about 5% in both pixel-and object-based classifications. According to the results of pixel-based CCF classification, total burned area (i.e., moderate-high and high severity) was estimated as 813 ha and 2,546 ha for Menderes and Karabağlar fires, respectively. The difference between the pixel- and object-based classification estimation about the burned area coverage could be resulting from intraclass spectral heterogeneity about the image objects located in the burned regions of the study areas. Statistical analysis also revealed that the RotFor and CCF algorithms produced similar results in pixel-based and object-based classification for both fires.

Classification of urban tree species using multi-features derived from four-season RedEdge-MX data

In the remote sensing discrimination of tree species, the use of multi-temporal images may considerably improve the accuracy of recognising tree species. This study aimed to explore the effectiveness of the RedEdge-MX sensor, which was used to capture images during the key node period of tree growth, for driving the identification of tree species. The spectral band, texture and digital surface model (DSM) features of these data and their combinations were used as data sets, and 32 tree species were classified using maximum likelihood classification and random forest. The results demonstrated that the image imaging period considerably influenced the recognition of tree species. The recognition accuracy of tree flowering and leafing period data was the highest (52.98%, 86.66% and 86.90% based on spectral, texture and spectral + texture + DSM features, respectively), whereas that of the leafy period data was the lowest (34.32%, 82.39% and 82.81%). The classification accuracy significantly improved (72.76%, 91.51% and 92.16%) when multi-temporal data were combined. Moreover, the texture extraction window significantly affected the classification accuracy. The accuracy was low (70.47%, four seasons) when the minimum window was used, and this rate increased to 91.52% when the appropriate window was used but declined when an excessively large window was used. Furthermore, the classification accuracy obtained using texture features was higher than that of the spectral bands and DSMs were used. Their combination optimised the accuracy of tree species classification (92.16%). These results show that the capture of key node images in tree growth, the selection of appropriate texture extraction windows, and the use of multiple types of features can drive the effective recognition of urban greening tree species.

SatRed: New classification land use/land cover model based on multi-spectral satellite images and neural networks applied to a semiarid valley of Patagonia

In this article we describe a new model, SatRed, which classifies land use and land cover (LULC) from Sentinel-2 imagery and data acquired in the field. SatRed performs pixel-level classification and is based on a densely-connected neural network. The study site is the lower Chubut river valley which has an extension of 225 km2 and is located in estern semiarid Patagonia. SatRed showed a 0.909 ± 0.009% (mean ± sd, n = 7) overall accuracy and outperformed the seven most traditional Machine Learning methods, including Random Forest. Our model accurately predicted buildings, shrublands, pastures and water and yielded the best results with classes harder to classify by all methods considered (Fruit crops and Horticulture). Further improvements involving textural information and multi-temporal images are proposed. Our model proved to be easy to run and use, fast to execute and flexible. We highlight the capacity of SatRed to classify LULC in small study areas as compared to large data sets usually needed for state-of-the-art Deep Learning models suggested in literature.

Assessing Ecological Quality Based on Remote Sensing Images in Wugong Mountain

AbstractThis study takes multitemporal Landsat images as data source to explore the changes of Fractional Vegetation Cover (FVC) and ecological quality (EQ) of the Wugong Mountain (WGM). The regression model obtained from MODIS NDVI data was used to correct the temporal difference of Landsat normalized difference vegetation index (NDVI) data in 2019, and the Remote Sensing based Ecological Index (RSEI) was calculated to assess the change of FVC and EQ in WGM. Results showed that, in the past 25 yr, the mean value of FVC has increased from 0.795 in 1994 to 0.890 in 2019, which consequently improved EQ from 0.746 to 0.773 respectively. The relationship among topographic factors, FVC and EQ was analyzed by using elevation, slope, and aspect. The effect of topographic factor on FVC and EQ in WGM was in the order of slope, aspect, and elevation. The value of FVC and RSEI increased first and then decreased with increment of elevation and slope. In detail, the favorable terrain of FVC and EQ was the area with an elevation of 500–1,400 m and a slope of 8°–35°. The value of FVC and RSEI in semi‐sunny and sunny slopes were higher than that of shady slopes. The unfavorable terrain of FVC and EQ was the area of the meadow with an elevation greater than 1,700 m. This work highlights the importance of FVC and EQ which can provide scientific decision‐making for the sustainability of WGM, and coordinate development of ecological environment protection and economic construction.

The Suitability of PlanetScope Imagery for Mapping Rubber Plantations

Quickly and accurately understanding the spatial distribution of regional rubber resources is of great practical significance. Using the unique phenological characteristics of rubber trees derived from remotely sensed data is a common effective method for monitoring rubber trees. However, due to the lack of high-quality images available during the key phenological period, it is still very difficult to apply this method in practical applications. PlanetScope data with high temporal (daily) resolution have great advantages in acquiring high-quality images, but these images have not been previously used to monitor rubber plantations. In this paper, multitemporal PlanetScope images were used as data sources, and the spectral features, index features, first principal components, and textural features of the images were comprehensively utilized. Four classification methods, including a pixel-based random forest (RF) approach, pixel-based support vector machine (SVM) approach, object-oriented RF approach and object-oriented SVM approach, were utilized to discuss the feasibility of using PlanetScope data to monitor rubber forests. The results showed that the optimal time window for monitoring rubber forests in the study area spanned from the 49th day to the 65th day of 2019 according to the MODIS-NDVI analysis. The contribution rate of the difference in the modified simple ratio (dMSR) feature was largest among all considered features for all pixel-based and object-oriented methods. The object-oriented RF/SVM classification method achieved the best classification results with an overall accuracy of 93.87% and a Kappa index of agreement (KIA) of 0.92. The highest producer’s accuracy and user’s accuracy obtained with this method were 95.18% for rubber plantations. The results of this study show that it is feasible to use PlanetScope data to perform rubber monitoring, thus effectively solving the problem of missing images in the optimal rubber monitoring period; additionally, this method can be extended to other real-life applications.

Impacts of inter-annual cropland changes on land surface temperature based on multi-temporal thermal infrared images

The research on the impact of land cover changes on the thermal environment is crucial to environmental monitoring. Land surface temperature (LST) is often used as the main parameter to analyze the thermal environment. As the primary land cover type, “cropland” is the main factor affecting the LST. Previous studies investigated the effects of cropland with other land cover types on the LST but ignored the changes within cropland. Furthermore, inter-annual changes of crop types in the cropland often occur. With the growth of the crops, their impact on LST also change. Therefore, it is necessary to understand how cropland changes affect the LST. The traditional comparison method based on a single time image is not suitable for evaluating the impact of the different crops during the whole growth period because single-phase information cannot reflect the changing process of crop influence. To address this issue, this paper proposes a cumulative land surface temperature index (cLST) based on multi-temporal images to evaluate the yearly impact of cropland changes. Results indicate that different crops have different effects on the thermal environment, and the annual cLST of cotton extracted from MODIS is higher than that of corn, sorghum, and winter wheat cropland. Also, the changing amplitude of the annual cLST is mainly related to the inter-annual cropland area ratio change (R = 0.85 for winter wheat to cotton, R = 0.75 for corn to cotton) in the study area, indicating that the overall change from corn and winter wheat to cotton cropland increases the annual cLST. The effect of cotton-sorghum and winter wheat-corn change is not significant. By comparing the contribution rate, it is found that the annual cLST is more affected by the cotton-winter wheat change (35%) than air temperature (26%). The method proposed in this paper helps to reveal the impact of cropland changes on LST, and the prediction of regional climate changes.

Estimating fractional coverage of crop, crop residue, and bare soil using shortwave infrared angle index and Sentinel-2 MSI

ABSTRACT Accurate estimations of soil cover parameters (fractional coverage of crop residue [f cr], crop [f c], and bare soil [f bs]) in croplands can assist in decision-making for agricultural management organisations and are important for understanding the interrelations between global changes and terrestrial ecosystems. In recent decades, optical remote sensing has been widely used for mapping f c, f cr, and f bs. The crop residue and soil spectra decrease rapidly with increasing cropland moisture primarily because of water absorption in the near-infrared and shortwave infrared bands. This leads to a decrease in the denominator of current normalized crop residue spectral indices (shortwave infrared [SWIR] band 1 + band 2), thereby causing them to increase with increasing cropland moisture. This study revealed that the slopes of the soil and crop residue spectra between SWIR1 and SWIR2 were less affected by cropland moisture changes. Based on this feature, we propose a shortwave infrared angle (SWIRA) index and jointly use it with normalized difference vegetation index (NDVI) to estimate and produce multi-temporal maps of f c, f cr, and f bs using broadband Sentinel-2 MSI images. The proposed SWIRA is the slope of the spectrum between SWIR1 and SWIR2. This study (i) uses laboratory-based spectral reflectance to evaluate the performance of the SWIRA and (ii) further evaluates the performance of the SWIRA–NDVI method using multi-temporal Sentinel-2 MSI images. Our results indicate that (i) cropland moisture has a considerably smaller effect on SWIRA than it does on current broadband normalized crop residue spectral indices, and (ii) maps of the estimated f c, f cr, and f bs values can be used to improve crop growth and decision-making, for example, by providing harvest maps and soil tillage intensity maps.

Impact of Deforestation on Rural Livelihood in Mbieri, Imo State Nigeria

Globally the rate of deforestation and forest degradation is around 13million hectares, occurring mostly in developing countries. This study aimed at assessing the impact of deforestation on livelihood sources in Mbieri a rural community in Imo State, Southeast Nigeria. Multi-Temporal Satellite Images were analyzed for changes in land use and land cover in the area, while random sampling method was used to administer the questionnaire, and participatory rural appraisal (PRA) method was used to elicit information on drivers of deforestation, income levels and perceived effects of deforestation in the study area. Six land use/cover types were identified namely; farmland, bare soil, built-up surface, water bodies, secondary forest and primary forest. GPS coordinates of the sampled deforested areas were also recorded and used to overlay on the Satellite processed data on land use and land cover. Data were further obtained from the satellite imageries of Landsat 4, thematic mapper (TM) and Landsat 7 and 8 ETM+ covering the year 1986, 2000, and 2016 respectively. Results from satellite image analysis revealed that land use changes have negatively impacted deforestation leading to loss of primary forest and reduction in secondary forest. Built-up areas and farmland increased from 13.92% and 11.47% in 1986 to 32.86% and 21.97% in 2016 respectively. While the primary forest reduced from 35.94% in 1986 to 10.78% in 2016. Population increase and agricultural expansion were identified as the major drivers of deforestation in Mbieri. Impacts of deforestation on the people include loss of valuable species of flora and fauna, decreased earnings from the sale of forest resources and loss of farmland to erosion of exposed surfaces. It is recommended that forest plantations be increased by using vacant and unused lands which will have net positive benefits also, deliberate reforestation should be embarked on to avoid environmental degradation and possible increase in ambient temperature.

For-backward LSTM-based missing data reconstruction for time-series Landsat images

ABSTRACT Reconstructing the missing data for cloud/shadow-covered optical satellite images has great significance for enhancing the data availability and multi-temporal analysis. In this study, we proposed a deep-learning-based method for cloud/shadow-covered missing data reconstruction for time-series Landsat images. Central to this method is the combined use of autoencoder, long-short-term memory (AE-LSTM)-based similar pixel clustering and for backward LSTM-based time-series prediction. First, manually delineated cloud/shadow-covered masks were overlaid onto multi-temporal satellite images to produce pixel-wise time-series data with masking values. Second, these pixel-wise time series were clustered by an AE-LSTM-based unsupervised method into multiple clusters, for searching similar pixels. Third, for each cluster of target images, a for-backward-LSTM-based model was established to restore missing values in time series data. Finally, reconstructed data were merged with cloud-free (image) regions to produce cloud-free time-series images. The proposed method was applied onto three datasets of multi-temporal Landsat-8 OLI images to restore cloud/shadow-covered images. The reconstruction results, showing an improvement of greater than 10% in normalized mean-square error compared to the state-of-the-art methods, demonstrated the effectiveness of the proposed method in time-series reconstruction for satellite images.

Assessment of the Effectiveness of Sand-Control and Desertification in the Mu Us Desert, China

The first successful sand-control was achieved in the Mu Us Desert by local people in the 1950–1960s, and their experience and approach have been extended to the whole Ordos and Northern China since then. The objective of this paper is to assess comprehensively the effectiveness of sand-control in 15 counties in and around Mu Us using multitemporal satellite images and socioeconomic data. After atmospheric correction, Landsat TM and OLI images were harnessed for land cover classification based on the ground-truth data and for derivation of the GDVI (generalized difference vegetation index) to extract the biophysical changes of the managed desert and desertification. Climatic, socioeconomic, environmental and spatial factors were selected for coupling analysis by multiple linear and logistic regression models to reveal the driving forces of desertification and their spatial determinants. The results show that from 1991 to 2020, 8712 km2 or 63% of the desert has been converted into pastures and shrublands with a greenness increase of 0.3509 in GDVI; the effectiveness of sand-control is favored by the rational agropastoral activities and policies; though desertification occurs locally, it is associated with both climatic and socioeconomic factors, such as wind speed, precipitation, water availability, distance to roads and animal husbandry.

Reconstruction of high spectral resolution multispectral image using dictionary-based learning and sparse coding

With the rising development of imaging spectroscopy, there is an increase in demand for images with high spectral, spatial, and temporal resolution. This study proposes a reconstruction from low spectral resolution multispectral imagery to higher spectral resolution hyperspectral imagery to overcome the problem of low spatial resolution and less availability of multi-temporal hyperspectral images. This study proposes a novel approach to dictionary learning based on nonlinear unmixing for dense mixtures and linear unmixing for sparse mixtures. Additionally, least square-based sparse coding has been applied in this framework to reconstruct high-resolution spectra from low-resolution spectra. The proposed method has been implemented on standard as well as real datasets and the performance of reconstruction has been validated through parametric techniques. The proposed method has been compared with states of the art methods like Joint Sparse & Low-Ranking Method and Derivative based Learning Method and it is observed that the proposed method outperforms the other methods. Nonlinear Spectral Unmixing has been performed and classification accuracy has been assessed on regenerated image data and observed to produce satisfactory output. In this study, the regenerated high spectral resolution image has been used for species-level classification and mapping of pure and mixed patches of mangrove species and the output compared with the Hyperion hyperspectral dataset of Henry Island, Sunderbans, India. Similarly, the proposed algorithm has also been applied on the Indian Pines, Salinas, Cuprite and Jasper Ridge datasets and the regenerated high spectral resolution images have been used for subpixel level target detection and classification.

Three-Dimensional Convolutional Neural Network on Multi-Temporal Synthetic Aperture Radar Images for Urban Flood Potential Mapping in Jakarta

Flooding in urban areas is counted as a significant disaster that must be correctly mitigated due to the huge amount of affected people, material losses, hampered economic activity, and flood-related diseases. One of the technologies available for disaster mitigation and prevention is satellites providing image data on previously flooded areas. In most cases, floods occur in conjunction with heavy rain. Thus, from a satellite’s optical sensor, the flood area is mostly covered with clouds which indicates ineffective observation. One solution to this problem is to use Synthetic Aperture Radar (SAR) sensors by observing backscatter differences before and after flood events. This research proposes mapping the flood-prone areas using machine learning to classify the areas using the 3D CNN method. The method was applied on a combination of co-polarized and cross-polarized SAR multi-temporal image datasets covering Jakarta City and the coastal area of Bekasi Regency. Testing with multiple combinations of training/testing data proportion split and a different number of epochs gave the optimum performance at an 80/20 split with 150 epochs achieving an overall accuracy of 0.71 after training in 283 min.

Land use/land cover changes of Noyyal watershed in Coimbatore district, India, mapped using remote sensing techniques.

The present study undertakes to produce the land use/land cover map and to explore the change detection analysis of Noyyal watershed, Coimbatore, for a time period of 18years. Based on the remote sensing and geographical information system for monitoring the temporal variations of land use/land cover, multi-temporal Landsat satellite 30-m spatial resolution images of Landsat 4/5 MSS and TM (1999), Landsat 7 ETM + (2008), and Landsat 8 Operational Land Imager (OLI) were obtained from the USGS website. The satellite images were geocoded into the universal transverse mercator (UTM) coordinate system zone 43N. The unsupervised classification method was done by using an iterative self-organizing data analysis algorithm to compare the images and to classify the images into various land cover categories. Kappa statistics were used to assess the validation of the present study. The analysis suggests the total forest covered in 1999 was 22.69% and that of 2008 was 24.04% and reduced to 6.09%, in 2017. The agricultural land of 17.8% is reduced to 3.11% in 2008 and 0.86% in 2017. The settlements increased from 15.59 to 24.21% in 2008 and 27.14% in 2017. Increase in deforestation leads to increase in barren land. In 1999, the percentage of barren land was 17.2%; in 2008, it was 13.19%, and 50.93% in 2017. The overall accuracy estimation of the study is 73.19% and Kappa coefficient is 0.72. This study has proven a substantial strength of agreement for the map of 2017 from the result of validation rating criteria of Kappa statistics.

Monitoring ecosystem services in the Guangdong-Hong Kong-Macao Greater Bay Area based on multi-temporal deep learning

Assessment of ecosystem service supply and demand, as well as the budgets of ecosystem service supply and demand, is the basis of scientific urban planning. In the 20 years between the proposal and formation of the Guangdong-Hong Kong-Macao Greater Bay Area (GBA), the natural ecosystem has been degraded and the ecological balance has been destroyed. In this paper, in order to assess the changes in ecosystem services in the GBA, a deep learning method composed of deep change vector analysis and the ResUnet model is proposed to achieve land use/land cover (LULC) mapping for 2000 and 2020. An index-based non-monetary evaluation method is then employed to quantify the value of the ecosystem services, and the spatial and temporal characteristics of the ecosystem service changes are analyzed. The results reveal that: (1) the proposed deep learning approach that combines deep change vector analysis (CVA) and model fine-tuning is able to achieve rapid and efficient LULC mapping in a large-scale area with multi-temporal image sequences. The overall accuracy of LULC mapping is 86.06% for 2000 and 86.67% for 2020. (2) The impervious surface area of all the cities in the GBA has increased significantly between 2000 and 2020, with an overall increase of 11.95%. (3) The mismatch between supply and demand for ecosystem services in the GBA has intensified, especially for provisioning, regulation, and cultural services. (4) The spatial distribution of the ecosystem service budget changes in the GBA shows aggregation characteristics and spatially positive correlation. These findings will provide important insights for promoting the coordinated development of the regional ecosystems and social economy in the GBA.

Detection of seasonal land use pattern and irrigated crops in drylands using multi-temporal sentinel images

Detection of seasonal land use pattern and irrigated crops in drylands using multi-temporal sentinel images

Geo-environmental monitoring of coastal and land resources of Port Said Governorate, Egypt

Port Said Governorate is one of the distinguished Egyptian coastal areas in regard to location, activities and resources. Present study aims to evaluate spatial and temporal changes in Land Use/Cover (LULC), Land Surface Temperature (LST) and Shoreline as a result of natural and anthropogenic factors using geospatial techniques. To achieve this aim, four calibrated multi-temporal Landsat images dated 1998, 2008, 2018 and 2021 integrated with field surveys were processed. Nine main LULC classes were mapped; urban, fish farms, vegetation, aquatic plants, main roads, bare land, water, canals/drains and salty areas. Developmental projects, particularly reclamation and urbanization, accelerated the increase in urban and agricultural lands during the whole period of study. Maximum rate of urban expansion was reported during the last period (2018–2021) and for agricultural lands during 2008–2018. The south eastern parts showed a continuous annual increase in the fish farms from 2.04 to 6.54 to 65.16 km2 at 1998, 2008, 2018 and 2021, respectively. Further, the last periods showed an increase in the main roads due to the construction of “30 June Road”. A small variation is observed in mean LST recording 34.2, 33.7 and 34.3, 34.2° C at 1998, 2008, 2018 and 2021, respectively. LULC can be ordered from lowest to highest LST as following; water (27.1 °C), aquatic plants (28.1 °C), fish farms (30.6 °C), vegetation (31.9 °C), canals and drains (33.8 °C), urban (36.45 °C), salty areas (36.6 °C), main roads (37.20 °C) and bare land (39.40 °C). The total eroded area along Port Said shoreline (5 km2) exceeds the total accreted areas (2.8 km2). Maximum erosion and accretion were observed at the eastern sector recording 2.61 and 1.29 km2, respectively. Fortunately, no intensive urban and agricultural areas are located in this sector which minimizes the probable adverse impact.

Quantitatively Assessing the Future Land-Use/Land-Cover Changes and Their Driving Factors in the Upper Stream of the Awash River Based on the CA–Markov Model and Their Implications for Water Resources Management

Despite the rapid economic and population growth, the risks related to the current dynamics of land use and land cover (LULC) have attracted a lot of attention in Ethiopia. Therefore, a complete investigation of past and future LULC changes is essential for sustainable water resources and land-use planning and management. Since the 1980s, LULC change has been detected in the upper stream of the Awash River basin. The main purpose of this research was to investigate the current dynamics of LULC and use the combined application of the cellular automata and the Markov chain (CA–Markov) model to simulate the year 2038 LULC in the future; key informant interviews, household surveys, focus group discussions, and field observations were used to assess the consequences and drivers of LULC changes in the upstream Awash basin (USAB). This research highlighted the importance of remote sensing (RS) and geographic information system (GIS) techniques for analyzing the LULC changes in the USAB. Multi-temporal cloud-free Landsat images of three sequential data sets for the periods (1984, 2000, and 2019) were employed to classify based on supervised classification and map LULC changes. Satellite imagery enhancement techniques were performed to improve and visualize the image for interpretation. ArcGIS10.4 and IDRISI software was used for LULC classification, data processing, and analyses. Based on Landsat 5 TM-GLS 1984, Landsat 7 ETM-GLS 2000, and Landsat 8 2019 OLI-TIRS, the supervised maximum likelihood image classification method was used to map the LULC dynamics. Landsat images from 1984, 2000, and 2019 were classified to simulate possible LULC in 2019 and 2038. The result reveals that the maximum area is covered by agricultural land and shrubland. It showed, to the areal extent, a substantial increase in agricultural land and urbanization and a decrease in shrubland, forest, grassland, and water. The LULC dynamics showed that those larger change rates were observed from forest and shrubland to agricultural areas. The results of the study show the radical changes in LULC during 1984–2019; the main reasons for this were agricultural expansion and urbanization. From 1984 to 2019, agriculture increased by 62%, urban area increased by 570.5%, and forest decreased by 88.7%. In the same year, the area of shrubland decreased by 68.6%, the area of water decreased by 65.5%, and the area of grassland decreased by 57.7%. In view of the greater increase in agricultural land and urbanization, as well as the decrease in shrubland, it means that the LULC of the region has changed. This research provides valuable information for water resources managers and land-use planners to make changes in the improvement of future LULC policies and development of sub-basin management strategies in the context of sustainable water resources and land-use planning and management.

Segmentation of multi-temporal polarimetric SAR data based on mean-shift and spectral graph partitioning.

Polarimetric SAR (PolSAR) image segmentation is a key step in its interpretation. For the targets with time series changes, the single-temporal PolSAR image segmentation algorithm is difficult to provide correct segmentation results for its target recognition, time series analysis and other applications. For this, a new algorithm for multi-temporal PolSAR image segmentation is proposed in this paper. Firstly, the over-segmentation of single-temporal PolSAR images is carried out by the mean-shift algorithm, and the over-segmentation results of single-temporal PolSAR are combined to get the over-segmentation results of multi-temporal PolSAR images. Secondly, the edge detectors are constructed to extract the edge information of single-temporal PolSAR images and fuse them to get the edge fusion results of multi-temporal PolSAR images. Then, the similarity measurement matrix is constructed based on the over-segmentation results and edge fusion results of multi-temporal PolSAR images. Finally, the normalized cut criterion is used to complete the segmentation of multi-temporal PolSAR images. The performance of the proposed algorithm is verified based on three temporal PolSAR images of Radarsat-2, and compared with the segmentation algorithm of single-temporal PolSAR image. Experimental results revealed the following findings: (1) The proposed algorithm effectively realizes the segmentation of multi-temporal PolSAR images, and achieves ideal segmentation results. Moreover, the segmentation details are excellent, and the region consistency is good. The objects which can’t be distinguished by the single-temporal PolSAR image segmentation algorithm can be segmented. (2) The segmentation accuracy of the proposed multi-temporal algorithm is up to 86.5%, which is significantly higher than that of the single-temporal PolSAR image segmentation algorithm. In general, the segmentation result of proposed algorithm is closer to the optimal segmentation. The optimal segmentation of farmland parcel objects to meet the needs of agricultural production is realized. This lays a good foundation for the further interpretation of multi-temporal PolSAR image.