Satellite Image Time Series Research Articles

Partition of Marine Environment Dynamics According to Remote Sensing Reflectance and Relations of Dynamics to Physical Factors

Seawaters exhibit various types of cyclic and trend-like temporal alterations in their biological, physical, and chemical processes. Surface water dynamics may vary, for instance, when the timings, durations, or amplitudes of seasonal developments of water properties alter between years and locations. We introduce a workflow using remote sensing to identify surface waters undergoing similar dynamics. The method, called ocean surface dynamics partitioning, classifies pixels based on their temporal change patterns instead of their properties at successive time snapshots. We apply an efficient parallel computing method to calculate Dynamic Time Warping (DTW) time series distances of large datasets of Earth Observation MERIS-instrument reflectance data Rrs(510 nm) and Rrs(620 nm), and produce a matrix of time series distances between 12,252 locations/time series in the Baltic Sea, for both wavelengths. We define cluster prototypes by hierarchical clustering of distance matrices and use them as initial prototypes for an iterative process of partitional clustering in order to identify areas that have similar reflectance dynamics. Lastly, we compute distances from the time series of the reflectance data to selected physical factors (wind, precipitation, and changes in sea surface temperature) obtained from Copernicus data archives. The workflow is reproducible and capable of managing large datasets in reasonable computation times and identifying areas of distinctive dynamics. The results show spatially coherent and logical areas without a priori information about the locations of the satellite image time series. The alignments of the reflectance time series vs. the observational time series of the physical environment clarify the causalities behind the cluster formation. We conclude that following the changes in an aquatic realm by biogeochemical observations at certain temporal intervals alone is not sufficient to identify environmental shifts. We foresee that the changes in dynamics are a sensitive measure of environmental threats and therefore they will be important to follow in the future.

A novel CNN-LSTM-based approach to predict urban expansion

Time-series remote sensing data offer a rich source of information that can be used in a wide range of applications, from monitoring changes in land cover to surveillance of crops, coastal changes, flood risk assessment, and urban sprawl. In this paper, time-series satellite images are used to predict urban expansion. As the ground truth is not available in time-series satellite images, an unsupervised image segmentation method based on deep learning is used to generate the ground truth for training and validation. The automated annotated images are then manually validated using Google Maps to generate the ground truth. The remaining data were then manually annotated. Prediction of urban expansion is achieved by using a ConvLSTM network, which can learn the global spatio-temporal information without shrinking the size of spatial feature maps. The ConvLSTM based model is applied on the time-series satellite images and the results of prediction are compared with Pix2pix and Dual GAN networks. In this paper, experimental results are conducted using several multi-date satellite images representing the three largest cities in Saudi Arabia, namely: Riyadh, Jeddah, and Dammam. The evaluation results show that the proposed ConvLSTM based model produced better prediction results in terms of Mean Square Error, Root Mean Square Error, Peak Signal to Noise Ratio, Structural Similarity Index, and overall classification accuracy as compared to Pix2pix and Dual GAN. Moreover, the training time of the proposed architecture is less than the Dual GAN architecture.

Deep-STaR: Classification of image time series based on spatio-temporal representations

Image time series (ITS) represent complex 3D (2D+t in practice) data that are now daily produced in various domains, from medical imaging to remote sensing. They contain rich spatio-temporal information allowing the observation of the evolution of a sensed scene over time. In this work, we focus on the classification task of ITS, as often available in remote sensing tasks. An underlying problem here is to consider jointly the spatial and the temporal dimensions of the data. We present Deep-STaR, a method to learn such features from ITS data to proceed to their classification. Instead of reasoning in the original 2D+t space, we investigate novel 2D planar data representations, containing both temporal and spatial information. Such representations are a novel way to structure the ITS, compatible with deep learning architectures. They are used to feed a convolutional neural network to learn spatio-temporal features with 2D convolutions, leading ultimately to classification decision. To enhance the explainability of the results, we also propose a post-hoc attention mechanism, enabled by this new approach, providing a semantic map giving some insights for the taken decision. Deep-STaR is evaluated on a remote sensing application, for the classification of agricultural crops from satellite ITS. The results highlight the benefice of this method, compared to the literature, and its interest to make easier the interpretation of ITS to understand spatio-temporal phenomena.

Quality control and class noise reduction of satellite image time series

The extensive amount of Earth observation satellite images available brings opportunities and challenges for land mapping in global and regional scales. These large datasets have motivated the use of satellite image time series analysis coupled with machine learning techniques to produce land use and cover class maps. To be successful, these methods need good quality training samples, which are the most important factor for determining the accuracy of the results. For this reason, training samples need methods for quality control of class noise. In this paper, we propose a method to assess and improve the quality of satellite image time series training data. The method uses self-organizing maps (SOM) to produce clusters of time series and Bayesian inference to assess intra-cluster and inter-cluster similarity. Consistent samples of a class will be part of a neighborhood of clusters in the SOM map. Noisy samples will appear as outliers in the SOM. Using Bayesian inference in the SOM neighborhoods, we can infer which samples are noisy. To illustrate the methods, we present a case study in a large training set of land use and cover classes in the Cerrado biome, Brazil. The results prove that the method is efficient to reduce class noise and to assess the spatio-temporal variation of satellite image time series training samples.

An automatic approach for detecting building fences from high-resolution images: the case study of Makkah, Saudi Arabia

Abstract In the light of the constantly expanding technological advancements concerning high-resolution satellites and imaging techniques for investigative and information uses it is important to look at how these algorithms progress to acquire more reliable data in a much efficient manner. This study aims to (1) investigate the ability to use remote sensing and geographic information system techniques to extract the detecting building edges in the City of Makkah and (2) investigate new machine learning techniques to derive the illegal building fences in the study area. Two WorldView-3 images will be the first obtained for the City of Makkah in 2016 and 2018. Convolutional neural networks algorithm will be investigated to detect all the fences within the two images. These traits have been utilized to create automated object detection techniques, which are a core requirement of information extraction and large frame analysis of images covering large expanses of land. In high-resolution images, object detection identifies objects belonging to a class, locating them using a bounding box. Based on satellite images time series, the outputs will detect the changes that occurred during 2016 and 2018. A web map application will be designed as the primary tool to make it easier, illustrating the differences between the main changes. Evaluation of binary classifiers approach will be used to evaluate the outcomes of building fences based on several performances that measure data interpretation. Preliminary findings will illustrate the precision and accuracy of the used machine learning algorithm. The research findings can contribute to the federal/municipal authorities and act as a generic indicator for targeting building fences for urban areas and/or suburban areas.

Analyzing the dynamics of urbanization in Delhi National Capital Region in India using satellite image time-series analysis

Understanding urban land-use changes and accurately quantifying urban land transitions is essential to global land-change research. The present study aimed to capture non-linear land transitions within urban areas using an automated change detection technique in a satellite image time series. Traditional land-use and cover maps used to map and monitor urban areas assume land change is a linear process and that urbanization is the last stage of land transition. In reality, however, most land transitions are non-linear. The present study focused on Delhi National Capital Territory, in India, and its adjacent major cities. A popular time-series analysis method was applied on MODIS NDVI time-series (2000–2017) data to detect change within the impervious surface area of the region. Overall validation and analysis of the results showed that the method was able to capture the direction and timing of the changes very well within all levels of urban density (except very high-density areas with more than 98% built-up density). The majority of urban areas in the region experienced interrupted, abrupt, and gradual greening. The results show different examples of non-linear land transitions detected from satellite images. Until recently, these land transitions could only be observed via long-term field surveys and/or local knowledge. The results reveal that the land-change trajectories can be different based on the level of built-up density, size of the urban area, physical proximity, and accessibility to relatively bigger urban areas. Knowledge gained from this study can be useful in better understanding the micro-climatic patterns and environmental quality within a city.

Long Time Series High-Quality and High-Consistency Land Cover Mapping Based on Machine Learning Method at Heihe River Basin

Long time series of land cover changes (LCCs) are critical in the analysis of long-term climate, environmental, and ecological changes. Although several moderate to fine resolution global land cover datasets have been publicly released and they show strong consistency at the global scale, they have large deviations at the regional scale; furthermore, high-quality land cover datasets from before 2000 are not available and the classification consistency among different datasets is not very good. Thus, long time series of land cover datasets with high quality and consistency are in great demand but they are still unavailable, even at the regional scale. The Landsat series of satellite imagery composed of eight successive satellites can be traced back to 1972 and it is, therefore, possible to produce a long time series land cover dataset. In addition, the newly available satellite data have the capability to construct time series satellite images and a time series analysis method such as LCMM can be employed for making high-quality land cover datasets. Therefore, by taking the advantages of the two categories of satellite data, we proposed a new time series land cover mapping method based on machine learning and it, thereafter, is applied to Heihe River Basin (HRB) for verification purposes. Firstly, the high-quality land cover datasets at HRB from 2011–2015, which were retrieved using the LCMM method, are used for quickly and accurately making training samples. Secondly, a strategy for transferring the training samples after 2011 to earlier years is established. Thirdly, the random forest model is employed to train the selected yearly samples and a land cover map for every year is subsequently made. Finally, comprehensive analysis and validation are carried out for evaluation. In this study, a long time series land cover dataset including 1986, 1990, 1995, 2000, 2005, 2010, 2011, 2012, 2013, 2014, and 2015 is finally made and an average precision of about 90% is achieved. It is the longest time series land cover map with 30 m resolution at HRB and the dataset has good time continuity and stability.

Estimation of erosion induced nutrients loss under different land uses: A case study in Miandam Valley, Swat Pakistan

In order to design Sustainable Land Management (SLM) plans or interventions it is important to understand the land use change and subsequent impacts. The basic aim of this study was to assess the impact of land use land cover (LULC) change on soil physico-chemical properties and nutrients loss under different land use/land cover changes within Miandam watershed of Swat valley, Pakistan. The study area was divided into three major types on the basis LULC type (Dense forest, Moderate forest and Agriculture land). A total of 81 soil samples were collected from the study area (27 from each land use) through stratified random sampling and were transferred to the laboratory. The prepared soil samples were then tested for various physico-chemical properties such as pH, electrical conductivity, contents of organic matter, organic carbon, sand, silt, clay, nitrogen, phosphorus, potassium, iron, copper and zinc. Results showed that LULC significantly affected all soil parameters except electrical conductivity and potassium. For all the nutrients assessed, the enrichment ratio was greater than 1 which showed that the most fertile layer of the soil in the cropped areas was transported through soil erosion. In this study, time-series satellite images were used to determine the spatiotemporal changes in the LULC of Miandam valley of Swat, Pakistan, and the possible effect of LULC on soil properties was reported. The information generated on the soil properties as indicators of soil health could be used to inform the stakeholders about the effect of LULC change in the study area. Multi-temporal image acquired by Landsat sensors for the year 2018 was used for quantifying changes in the study area. The Landsat images for the year 2018 were classified into six land cover/land use classes. The increase in agricultural activities caused an increase in the land farming areas which led to an increase in the rate of deforestation in the valley. Thus, the present study results reveal that the use of the soil for agriculture instead of keeping them naturally or in other words changes in the land use land cover affects the soil physico-chemical properties and the overall nutrients availability. Keywords: land use/land cover, soil properties, soil nutrients, Miandam, Swat valley DOI: 10.25165/j.ijabe.20211402.5704 Citation: Yousaf N, Khan B, Flanagan D C, Mian I A, Iqbal J, Rashid I, et al. Estimation of erosion induced nutrients loss under different land uses: A case study in Miandam Valley, Swat Pakistan. Int J Agric & Biol Eng, 2021; 14(2): 135–141.

Exploring influence factors in mapping soil organic carbon on low-relief agricultural lands using time series of remote sensing data

Soil organic carbon (SOC) content is of critical importance in managing agricultural fields and understanding carbon fluxes at various scales. At regional and global scales, digital mapping of SOC has been successful using environmental variables such as climatic, land use and terrain factors. However, such a mapping for agricultural lands in low-relief areas cannot be resolved due to weak spatial variations of the environmental variables. An alternative approach, based on time series of remote sensing images, has recently been emphasized in estimating SOC since crop growth status clearly revealed by satellite images is strongly related to SOC. However, there is still a lack of full understanding of impacts of factors such as data source, regression techniques, and spatial resolution on the accuracy of SOC mapping using time series of satellite images. In this study, prediction variables including four spectral bands (i.e., blue, green, red, and near-infrared bands) and the normalized difference vegetation index (NDVI) from Sentinel 2, Gaofen (GF) 1, and Landsat 8 data, acquired between November 2017 to March 2018, were individually used to estimate SOC by stepwise regression (STR), partial least squares regression (PLSR), and extreme learning machine (ELM). Besides, we further explored the influence of satellite parameters, such as scanning time, spectral bands and vegetation indices on predicting SOC using Sentinel 2 time series images. Results showed that: (1) the time series of remote sensing images can be used to map SOC in small- and large-extent low-relief areas with low evaluated root mean square errors (0.199 % and 0.249 %) and high R2 (0.555 and 0.528), (2) SOC estimations from the Sentinel-2 time series images, compared to those from Landsat 8 and GF 1 datasets, exhibited a better accuracy, and the ELM yielded a better prediction accuracy than PLSR and STR, (3) the satellite parameters of the spatial resolution, the acquisition time and the spectral bands significantly affected the prediction accuracy. This study offers more comprehensive information than terrain factors for revealing the influence of satellite parameters on predicting SOC, and provides great help for constructing one more suitable and higher precision soil mapping strategy for agricultural lands in low-relief areas.

Exploring Short-Term Climate Change Effects on Rangelands and Broad-Leaved Forests by Free Satellite Data in Aosta Valley (Northwest Italy)

Satellite remote sensing is a power tool for the long-term monitoring of vegetation. This work, with reference to a regional case study, investigates remote sensing potentialities for describing the annual phenology of rangelands and broad-leaved forests at the landscape level with the aim of detecting eventual effects of climate change in the Alpine region of the Aosta Valley (Northwest (NW) Italy). A first analysis was aimed at estimating phenological metrics (PMs) from satellite images time series and testing the presence of trends along time. A further investigation concerned evapotranspiration from vegetation (ET) and its variation along the years. Additionally, in both the cases the following meteorological patterns were considered: air temperature anomalies, precipitation trends and the timing of yearly seasonal snow melt. The analysis was based on the time series (TS) of different MODIS collections datasets together with Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS) collection obtained through Google Earth Engine. Ground weather stations data from the Centro Funzionale VdA ranging from 2000 to 2019 were used. In particular, the MOD13Q1 v.6, MOD16A2 and MOD10A1 v.6 collections were used to derive PMs, ET and snow cover maps. The SRTM (shuttle radar topography mission) DTM (digital terrain model) was also used to describe local topography while the Coordination of Information on the Environment (CORINE) land cover map was adopted to investigate land use classes. Averagely in the area, rangelands and broad-leaved forests showed that the length of season is getting longer, with a general advance of the SOS (start of the season) and a delay in the EOS (end of the season). With reference to ET, significant increasing trends were generally observed. The water requirement from vegetation appeared to have averagely risen about 0.05 Kg·m−2 (about 0.5%) per year in the period 2000–2019, for a total increase of about 1 Kg·m−2 in 20 years (corresponding to a percentage difference in water requirement from vegetation of about 8%). This aspect can be particularly relevant in the bottom of the central valley, where the precipitations have shown a statistically significant decreasing trend in the period 2000–2019 (conversely, no significant variation was found in the whole territory). Additionally, the snowpack timing persistence showed a general reduction trend. PMs and ET and air temperature anomalies, as well as snow cover melting, proved to have significantly changed their values in the last 20 years, with a continuous progressive trend. The results encourage the adoption of remote sensing to monitor climate change effects on alpine vegetation, with particular focus on the relationship between phenology and other abiotic factors permitting an effective technological transfer.

Relative Sea-Level Rise Scenario for 2100 along the Coast of South Eastern Sicily (Italy) by InSAR Data, Satellite Images and High-Resolution Topography

The global sea-level rise (SLR) projections for the next few decades are the basis for developing flooding maps that depict the expected hazard scenarios. However, the spatially variable land subsidence has generally not been considered in the current projections. In this study, we use geodetic data from global navigation satellite system (GNSS), synthetic aperture radar interferometric measurements (InSAR) and sea-level data from tidal stations to show the combined effects of land subsidence and SLR along the coast between Catania and Marzamemi, in south-eastern Sicily (southern Italy). This is one of the most active tectonic areas of the Mediterranean basin, which drives accelerated SLR, continuous coastal retreat and increasing effects of flooding and storms surges. We focus on six selected areas, which show valuable coastal infrastructures and natural reserves where the expected SLR in the next few years could be a potential cause of significant land flooding and morphological changes of the coastal strip. Through a multidisciplinary study, the multi-temporal flooding scenarios until 2100, have been estimated. Results are based on the spatially variable rates of vertical land movements (VLM), the topographic features of the area provided by airborne Light Detection And Ranging (LiDAR) data and the Intergovernmental Panel on Climate Change (IPCC) projections of SLR in the Representative Concentration Pathways RCP 2.6 and RCP 8.5 emission scenarios. In addition, from the analysis of the time series of optical satellite images, a coastal retreat up to 70 m has been observed at the Ciane river mouth (Siracusa) in the time span 2001–2019. Our results show a diffuse land subsidence locally exceeding 10 ± 2.5 mm/year in some areas, due to compacting artificial landfill, salt marshes and Holocene soft deposits. Given ongoing land subsidence, a high end of RSLR in the RCP 8.5 at 0.52 ± 0.05 m and 1.52 ± 0.13 m is expected for 2050 AD and 2100 AD, respectively, with an exposed area of about 9.7 km2 that will be vulnerable to inundation in the next 80 years.

Temporal unmixing-based cloud removal algorithm for optically complex water images

ABSTRACT Remote sensing has become an essential technique in water environment monitoring. However, the cloud contamination of remote sensing images breaks its spatial and temporal continuity in practical application. The current cloud removal algorithms always based on the hypothesis that the ground surface has no significant changes temporally, which is not proper for optically complex water body. Therefore, to overcome the weakness of current cloud removal algorithms on temporally fast-changing landscapes, a temporal unmixing-based cloud removal (TUBCR) algorithm is proposed to estimate the under-cloud information of optically complex water images. In this algorithm, the spatial information and temporal information were separated into temporal abundance images and temporal endmembers. By extracting the high temporal resolution endmembers, the fast-changing water information were estimated. The performance of the proposed algorithm was compared with those of two widely used cloud removal algorithms: the modified neighbourhood similar pixel interpolator (mNSPI) algorithm and the weighted linear regression (WLR) algorithm. The results of four simulated datasets (500 images in total) and two real Geostationary Ocean Colour Imager (GOCI) datasets (8 images in total) show that the proposed algorithm performed better in both quantitative indexes and visual effect compared with the mNSPI algorithm and the WLR algorithm. In satellite image time series, the proposed algorithm could accurately estimate under-cloud water information and correct the offsets of the statistical temporal trends that caused by cloud contamination. Hence, theoretically, the proposed TUBCR algorithm altered the similar pixel-based strategy of classic methods and got a satisfied performance in fast-changing water images. In applications, the TUBCR algorithm has great potential to improve the spatiotemporal coverage of optically complex water remote sensing.

Identifying Spatiotemporal Patterns in Land Use and Cover Samples from Satellite Image Time Series

The use of satellite image time series analysis and machine learning methods brings new opportunities and challenges for land use and cover changes (LUCC) mapping over large areas. One of these challenges is the need for samples that properly represent the high variability of land used and cover classes over large areas to train supervised machine learning methods and to produce accurate LUCC maps. This paper addresses this challenge and presents a method to identify spatiotemporal patterns in land use and cover samples to infer subclasses through the phenological and spectral information provided by satellite image time series. The proposed method uses self-organizing maps (SOMs) to reduce the data dimensionality creating primary clusters. From these primary clusters, it uses hierarchical clustering to create subclusters that recognize intra-class variability intrinsic to different regions and periods, mainly in large areas and multiple years. To show how the method works, we use MODIS image time series associated to samples of cropland and pasture classes over the Cerrado biome in Brazil. The results prove that the proposed method is suitable for identifying spatiotemporal patterns in land use and cover samples that can be used to infer subclasses, mainly for crop-types.

A Bayesian-inspired, deep learning-based, semi-supervised domain adaptation technique for land cover mapping

Land cover maps are a vital input variable to many types of environmental research and management. While they can be produced automatically by machine learning techniques, these techniques require substantial training data to achieve high levels of accuracy, which are not always available. One technique researchers use when labelled training data are scarce is domain adaptation (DA)—where data from an alternate region, known as the source domain, are used to train a classifier and this model is adapted to map the study region, or target domain. The scenario we address in this paper is known as semi-supervised DA, where some labelled samples are available in the target domain. In this paper we present Sourcerer, a Bayesian-inspired, deep learning-based, semi-supervised DA technique for producing land cover maps from satellite image time series (SITS) data. The technique takes a convolutional neural network trained on a source domain and then trains further on the available target domain with a novel regularizer applied to the model weights. The regularizer adjusts the degree to which the model is modified to fit the target data, limiting the degree of change when the target data are few in number and increasing it as target data quantity increases. Our experiments on Sentinel-2 time series images compare Sourcerer with two state-of-the-art semi-supervised domain adaptation techniques and four baseline models. We show that on two different source-target domain pairings Sourcerer outperforms all other methods for any quantity of labelled target data available. In fact, the results on the more difficult target domain show that the starting accuracy of Sourcerer (when no labelled target data are available), 74.2%, is greater than the next-best state-of-the-art method trained on 20,000 labelled target instances.

Joint Supervised Classification and Reconstruction of Irregularly Sampled Satellite Image Times Series

Recent satellite missions have led to a huge amount of Earth observation data, most of them being freely available. In such a context, satellite image time series have been used to study land use and land cover information. However, optical time series, such as Sentinel-2 or Landsat ones, are provided with an irregular time sampling for different spatial locations, and images may contain clouds and shadows. Thus, preprocessing techniques are usually required to properly classify such data. The proposed approach is able to deal with irregular temporal sampling and missing data directly in the classification process. It is based on Gaussian processes and allows to perform jointly the classification of the pixel labels as well as the reconstruction of the pixel time series. The method complexity scales linearly with the number of pixels, making it amenable in large-scale scenarios. Experimental classification and reconstruction results show that the method does not compete yet with state-of-the-art classifiers but yields reconstructions that are robust with respect to the presence of undetected clouds or shadows and does not require any temporal preprocessing.

A Nonlinear Radiometric Normalization Model for Satellite Imgaes Time Series Based on Artificial Neural Networks and Greedy Algroithm

Satellite Image Time Series (SITS) is a data set that includes satellite images across several years with a high acquisition rate. Radiometric normalization is a fundamental and important preprocessing method for remote sensing applications using SITS due to the radiometric distortion caused by noise between images. Normalizing the subject image based on the reference image is a general strategy when using traditional radiometric normalization methods to normalize multi-temporal imagery (usually two or three scenes in different time phases). However, these methods are unsuitable for calibrating SITS because they cannot minimize the radiometric distortion between any pair of images in SITS. The existing relative radiometric normalization methods for SITS are based on linear assumptions, which cannot effectively reduce nonlinear radiometric distortion caused by continuously changing noise in SITS. To overcome this problem and obtain a more accurate SITS, we propose a nonlinear radiometric normalization model (NMAG) for SITS based on Artificial Neural Networks (ANN) and Greedy Algorithm (GA). In this method, GA is used to determine the correction order of SITS and calculate the error between the image to be corrected and normalized images, which avoids the selection of a single reference image. ANN is used to obtain the optimal solution of error function, which minimizes the radiometric distortion between different images in SITS. The SITS composed of 21 Landsat-8 images in Tianjin, China, from October 2017 to January 2019 was selected to test the method. We compared NMAG with other two contrast methods (Contrast Method 1 (CM1) and Contrast Method 2 (CM2)), and found that the average root mean square error (μRMSE) of NMAG (497.22) is significantly smaller than those of CM1 (641.39) and CM2 (543.47), and the accuracy of normalized SITS obtained using NMAG increases by 22.4% and 8.5% compared with CM1 and CM2, respectively. These experimental results confirm the effectiveness of NMAG in reducing radiometric distortion caused by continuously changing noise between images in SITS.

Measuring dam induced alteration in water richness and eco-hydrological deficit in flood plain wetland

Along with wetland loss, the damming effect on hydrological modification in wetland is another less debated and challenging topic, which needs to have urgent attention. The present work intended to investigate the damming effect on the water richness and eco-hydrological condition of the floodplain wetland and its consequent ecological responses in Punarbhaba River Basin of India and Bangladesh. Satellite images derived hydro-period, water presence frequency (WPF), and water depth were generated for developing water richness model in pre (up to 1992) and post dam conditions (1993–2019). The range of variability (RVA) was modelled using time series satellite images based water index or normalized difference water index (NDWI). Based on RVA model, the hydrological failure rate was developed. Depth of water was used for preparing the flow duration curve (FDC) to estimate the eco-hydro-deficit and surplus condition in wetland at spatial scale for pre and post-dam periods. Satellite image based trophic state index models for pre and post dam conditions were constructed to investigate the ecological response of dam on floodplain wetlands. Results of water richness model showed that wetlands area under high wetland water richness zone decreased from 71.83% to 7.65% in the post-dam conditions. Results of hydrological failure rate showed that high failure rate captured 45% of total wetland area in the post-dam period. Results of eco-hydro-deficit exhibited that eco-hydro-deficit areas increased from 11.22% to 52.19% and 35.03%–52.67% respectively in post-dam conditions indicating growing ecological stress. The TSI models showed that most parts of the wetlands were converted from oligotrophic to meso-eutrophic state signifying the qualitative degradation of water and potential ecosystem health. The area under high TSI was observed in the wetland area having eco-hydro-deficit and high hydrological failure rate zones. These characteristics of wetland areas were found at the fringe of wetlands and fragmented smaller wetland units. The study concluded that damming over the Punarbhaba River adversely affected the water security of the floodplain wetlands in terms of modifying the hydrological richness, ecological condition of the wetland habitat, and ecological systems. The findings of the present study could provide a comprehensive research on the monitoring of surface water crisis in the wetlands, which will be the basic foundation to formulate water resource management plans for conservation, management and restoration of wetlands.

Recent Evolution of the Intertidal Sand Ridge Lines of the Dongsha Shoal in the Modern Radial Sand Ridges, East China.

The Dongsha Shoal is one of the largest shoals in the South Yellow Sea and has important marine ecological value. The shoal extends in a south–north direction and is controlled by the regional dominating tidal currents. Recently, due to human activities and some natural factors, the geomorphic dynamics of the Dongsha Shoal has undergone drastic changes. However, few people have proposed quantitative research on the changes of tidal flat morphology, let alone the long-term sequence analysis of sand ridge lines. Hence, we attempt to take the Dongsha Shoal in the Radial Sand Ridges as the research area, and analyze the trends of the long-term morphological evolution of the sand ridge lines over the period 1973–2016 based on a high-density time series of medium-resolution satellite images. The sand ridge line generally moves from southeast to northwest, and the position distribution of the sand ridge line from north to south has gradually changed from compact to scattered. We also found that the geomorphological dynamics at different positions of the sand ridge line are inconsistent. The north and south wings are eroded on the west side, while the central area is eroded on the east side. Most of the sand ridge line is moving eastward. In addition, the change of sand ridge line is affected by multiple factors such as sediment supply, typhoon, reclamation and laver cultivation.

Forest cover dynamics in Palas Valley Kohistan, Hindu Kush-Himalayan Mountains, Pakistan

Forest cover change in the mountainous region is driven by a variety of anthropogenic and natural factors. The Hindu Kush-Himalayan Mountains has experienced a considerable vegetation cover change due to intensive human activities, such as population growth, proximate causes, accessibility, unstable political situations, government policy failure and poverty. The present study seeks to find out the impact of population growth and road network expansion on forest cover of Palas valley based on remotely sensed data and employing geospatial techniques. Changes in forest cover were determined by classifying time-series satellite images of Landsat and Sentinel 2A. The images of October 1980, 2000, 2010 and 2017 were classified into six land cover classes and then the impact of population growth and accessibility on forest cover was analyzed. Furthermore, forest cover and land-use change detection map was prepared using classified images of 1980 and 2017. The data were collected mainly from field visits (ground verification), census reports, Communication and Works Department, Kohistan. Satellite imageries were obtained from the United States Geological Survey’s websites and classified in ERDAS imagine 2014 and ESRI ArcGIS 10.2.1 using supervised classification-maximum likelihood algorithm. Result of this study revealed that a substantial reduction in forest cover has taken place mainly in the proximity of human settlements. On the average, during the study period, annually more than 460 hectares of forest area has been converted into other uses.

Spatial domain bridge transfer : An automated paddy rice mapping method with no training data required and decreased image inputs for the large cloudy area

Paddy rice mapping in an accurate and timely manner was of significance as the explicitly spatial paddy rice maps played a critical role in food security and market stability. Over the decades, remote sensing (RS) techniques offered great potential to extract paddy rice from the optical satellite images. Two main categories of paddy rice mapping methods were commonly utilized. The first one was the phenology-oriented methods by utilizing the distinctive phenology of paddy rice, and the machine learning-based approaches were the other mainstream for paddy rice extraction by being recognized as a classification task. However, neither of the above methods were actually applicable to automatically map paddy rice for the large cloudy areas. The phenological methods were subject to the availability of time-series cloud-free RS inputs due to cloud contamination, and machine learning-based methods were often confined to the availability of high-quality collected training samples. Therefore, this study proposed a new flexible framework to integrate the above two methods, in an attempt to achieve the goal of automatic paddy rice mapping for large cloudy area. Firstly, phenological paddy rice mapping was implemented for the areas with cloud-free time series satellite images available to generate the paddy rice potentials. Following that, the derived paddy rice potentials were purified through filtering operations. Finally, the machine learning classifier was trained using the purified samples, and spatially transferred to other regions for the extraction of paddy rice. Several experiments were carried out to assess our proposed framework and the subsequent mapping results. The experimental results were promising, indicating that our framework contributed to overcoming the strong reliance on training data for machine learning methods, and reducing the number of multi-temporal inputs for automated paddy rice mapping, which potentially provided a new paradigm for the purpose of paddy rice extraction.