Multi-Temporal Remote Sensing Research Articles

Monitoring Land Use Changes in the Yellow River Delta Using Multi-Temporal Remote Sensing Data and Machine Learning from 2000 to 2020

The Yellow River Delta (YRD), known for its vast and diverse wetland ecosystem, is the largest estuarine delta in China. However, human activities and climate change have significantly degraded the wetland ecosystem in recent decades in the YRD. Therefore, an understanding of the land use modifications is essential for the efficient management and preservation of ecosystems in this region. This study utilized time series of remote sensing data and the extreme gradient boosting method to generate land use maps of the YRD from 2000 to 2020. Several methods, including transition matrix, land use dynamic degree, and standard deviation ellipse, were employed to explore the characteristics of land use transitions. The results underscore significant spatial variations in land use over the past two decades. The most rapid increase was observed in built-up area, followed by terrestrial water and tidal flats, while unutilized land experienced the fastest decrease, followed by forest–grassland. The spatial distribution patterns of agricultural land, built-up area, terrestrial water, and forest–grassland demonstrated stronger directionality compared to other land use types. The wetlands have expanded in size and improved in structure. Unutilized land has been converted into artificial wetlands comprising ponds, reservoirs, salt ponds, shrimp and crab ponds, and natural wetlands featuring mudflats and forest–grassland. The wetland conservation efforts after 2008 have proven very effective, playing a positive role in ecological and environmental preservation, as well as in regional sustainable development.

Multiscale and Multitemporal Remote Sensing for Neolithic Settlement Detection and Protection—The Case of Gorjani, Croatia

The decade of research concentrating on the area of Eastern Slavonia revealed an abundance of large and complex Middle and Late Neolithic sites. It changed profoundly how we perceive Middle and Late Neolithic settlements, including space, size and organization. The vast majority of these sites were detected through aerial reconnaissance and satellite image analysis. The observation of the sites was followed by intensive field surveys, which confirmed their attribution to the Middle and Late Neolithic period by surface finds. On those confirmed sites in the vicinity of Đakovo, Croatia, a magnetic survey was conducted on five sites, and the results confirmed the presence of large-scale Middle and Late Neolithic settlements with complex spatial organization and enclosure(s). The most complex remains so far are the sites Gorjani, Kremenjača and Topole, which we present in this paper, where one or two settlements remain covering an area of 70 hectares which is currently in the process of formal protection as a cultural landscape by the Ministry of Culture and Media of the Republic of Croatia. The special focus of this paper is the application of remote sensing in the detection, archaeological confirmation and protection of the site of Gorjani Topole.

Low-Cost Sensors and Multitemporal Remote Sensing for Operational Turbidity Monitoring in an East African Wetland Environment

Low-Cost Sensors and Multitemporal Remote Sensing for Operational Turbidity Monitoring in an East African Wetland Environment

Thick Cloud Removal in Multitemporal Remote Sensing Images via Low-Rank Regularized Self-Supervised Network

Thick Cloud Removal in Multitemporal Remote Sensing Images via Low-Rank Regularized Self-Supervised Network

Assessment of Spatio-Temporal changes of Forest Cover using Remote Sensing techniques in Pavagadh Region, Gujarat State

For effective forest management, it is essential to consider forest patterns and periodic changes in forest cover. Several spectral vegetation indices derived from multi-temporal Remote Sensing data are useful to track the changes over time. The major objective of this study was to monitor the changes in forest cover during the past three decades in the Pavagadh area of Panchmahal district, Gujarat State, India. Various indices like Normalized Difference Vegetation Index (NDVI), Land Surface Temperature, and Urban Thermal Field Variance Index (UTFVI) with the Ecological Evaluation Index were analyzed for assessment of Spatio-temporal changes in the forest cover. Multi-temporal Landsat-TM and OLI sensor data for the years 1991, 2001, 2011, and 2021 were utilized covering the study area. The results indicated that the total forest cover area has gradually increased from 1991 to 2021 and the total forest area has doubled during this period of 30 years. The comparative study of NDVI and Land Surface Temperature map brings out a significant fact that in the areas where moderate and dense forest cover is present, the Land Surface Temperature was lower as compared to areas with poor vegetation cover. This indicates that there is an inverse relationship between forest cover distribution and Land Surface Temperature. However, the Ecological evaluation index shows that the forest vegetation quality is gradually improving to normal conditions with the excellent category and UTFVI value (< 0) in reference to the year 1991.

A Framework for Retrieving Soil Organic Matter by Coupling Multi-Temporal Remote Sensing Images and Variable Selection in the Sanjiang Plain, China

Soil organic matter (SOM) is an important soil property for agricultural production. Rising grain demand has increased the intensity of cultivated land development in the Sanjiang Plain of China, and there is a strong demand for SOM monitoring in this region. Therefore, Baoqing County of the Sanjiang Plain, an important grain production area, was considered the study area. In the study, we proposed a framework for high-accuracy SOM retrieval by coupling multi-temporal remote sensing (RS) images and variable selection algorithms. A total of 73 surface soil samples (0–20 cm) were collected in 2010, and Landsat 5 images acquired during the bare soil period (April, May, and June) were selected from 2008 to 2011. Three variable selection algorithms, namely, Genetic Algorithm, Random Frog and Competitive Adaptive Reweighted Sampling (CARS), were combined with Partial Least Squares Regression (PLSR) to build SOM retrieval models on the spectral bands and indices of the images. The results using a single-date image showed that the combination of variable selection algorithms and PLSR outperformed using PLSR alone, and CARS showed the best performance (R2 = 0.34, RMSE = 15.66 g/kg) among all the algorithms. Therefore, only CARS was applied to SOM retrieval in the different year interval groups. To investigate the effect of the image acquisition time, all images were divided into various year interval groups, and the resulting images were then stacked. The results using multi-temporal images showed that the SOM retrieval accuracy improved as the year interval lengthened. The optimal result (R2 = 0.59, RMSE = 11.81 g/kg) was obtained from the 2008–2011 group, wherein the difference indices derived from the images of 2009, 2010, and 2011 dominated the selected spectral variables. Moreover, the spatial prediction of SOM based on the optimal model was consistent with the distribution of SOM. Our study suggested that the proposed framework that couples stacked multi-temporal RS images with variable selection algorithms has potential for SOM retrieval.

Correction: Yu et al. Landslide Susceptibility Mapping Based on Multitemporal Remote Sensing Image Change Detection and Multiexponential Band Math. Sustainability 2023, 15, 2226

The authors would like to make the following corrections about the published paper [...]

Mapping the Accumulation of Invasive Aquatic Plants in the Guadiana River, Spain, Using Multitemporal Remote Sensing

Multispectral remote sensing is very effective for the detection of different types of land cover. Satisfactory results have been obtained in the task of monitoring different types of vegetation covers using satellite images, including areas conquered by invasive aquatic plants such as water hyacinth. Several countries around the world are suffering from negative effects caused by the quick spread of these plants. For instance, several strategies have been carried out for their control and elimination in the Guadiana river, Spain. In this letter, we develop a new methodology capable of automatically finding the geo-location of the most frequent areas of accumulation of invasive aquatic plants in the Guadiana river. Our strategy exploits multispectral time series acquired by ESA’s Sentinel-2 satellite. Once the invasive plants have been detected using deep learning (a convolutional neural network), a subsequent analysis is carried out using geographic information systems to map the areas where water hyacinth patches are most frequently found. In this way, we demonstrate that the management of invasive aquatic plants in the Guadiana river can be successfully carried out.

A Robust Oriented Filter-Based Matching Method for Multisource, Multitemporal Remote Sensing Images

A Robust Oriented Filter-Based Matching Method for Multisource, Multitemporal Remote Sensing Images

Thick Cloud Removal for Multitemporal Remote Sensing Images: When Tensor Ring Decomposition Meets Gradient Domain Fidelity

Thick clouds in remote sensing (RS) images deteriorate the visual quality and hinder subsequent applications. The emerging multitemporal RS images with rich temporal information bring the opportunity for cloud removal. How to effectively exploit the rich temporal information of the multitemporal RS images remains challenging. As multitemporal RS images with the same geographic scene, the spatial gradient of RS images at different time nodes has a resemblance, which can guide the reconstruction of the cloudy region. Motivated by this, we suggest a gradient domain fidelity with respect to the guided gradient for thick cloud removal in multitemporal RS images, which faithfully preserves the fine edges and textures compared to the original pixel domain fidelity. Armed with the gradient domain fidelity, we propose a low-rank tensor ring decomposition model (TRGFid) for the thick cloud removal problem. In the proposed model, the guided gradient of the cloudy region is availably estimated by using the regression method from the cloud-free region of different time nodes. Moreover, we develop an efficient proximal alternating minimization-based algorithm for solving the proposed nonconvex model. Extensive simulated and real experiments show that the proposed method outperforms its competitors, and preserves fine edges and textures.

Dynamics of Low-Lying Sandy Coast of the Gydan Peninsula, Kara Sea, Russia, Based on Multi-Temporal Remote Sensing Data

The retreat rates of Arctic coasts have increased in recent decades at many sites, and an essential part of coasts considered accumulative before have turned erosional due to global climate changes and construction in the coastal zone. In this paper, we study a 7 km long coastal section of the western Gydan Peninsula in a new construction area. Based on the interpretation of multi-temporal satellite imagery, we assessed coastal dynamics in distinct periods from 1972 to 2020. We analyzed the geological structure of the coast as well as changes in hydrometeorological parameters with time, and considering the human impact, we proposed the main drivers of spatial and temporal variations of coastal dynamics. The studied low-lying sandy accumulative marine terrace was more or less stable in the period before construction (1972–2014). However, with the area’s development, the coast dynamics changed drastically: in 2014–2017, three-quarters of the studied area experienced retreat, and the average retreat rate amounted to 5.8 m/yr, up to 28.5 m/yr near the construction sites. We relate this coastal erosion intensification to human impact combined with the growth of hydrometeorological forcing. Although coastal erosion slowed down after 2017, the retreat trend remained. In the coming years, with Arctic climate warming, erosion of the studied coast will continue.

Monitoring Land Use/Cover Changes by Using Multi-Temporal Remote Sensing for Urban Hydrological Assessment: A Case Study in Beijing, China

Understanding the change in hydrological response due to urban dynamics is important for better flood preparedness and future sustainable urban planning. This study investigated the influence of urban land cover change on spatiotemporal changes in flood peak discharge and flood volume within a rapidly urbanizing catchment located in Beijing, China. We used Landsat satellite data ranging from 1986 to 2017 to monitor and quantify urban growth. Moreover, the Hydrological Modeling System (HEC-HMS) coupled with meteorological data was utilized to examine the impact of urban growth on hydrological responses. The results revealed that major changes in land use/cover (LULC) were detected in the urban landscape, which increased from 25.22% to 65.48% of the total catchment area, while agricultural land decreased from 64.85% to 25.28% during 1986–2017. The flood peak discharge and flood volume average of the three rainstorms events reached 7.02% and 11.93%, respectively. Furthermore, the changes in flood peak discharge and flood volume were more obvious at the sub-catchment scale. These findings indicate that urban growth enhanced the possible flooding risk in the study catchment. This study improves the understanding of the isolated impacts of urbanization on flooding and provides essential information for sustainable urban planning.

Google Earth Engine and Artificial Intelligence (AI): A Comprehensive Review

Remote sensing (RS) plays an important role gathering data in many critical domains (e.g., global climate change, risk assessment and vulnerability reduction of natural hazards, resilience of ecosystems, and urban planning). Retrieving, managing, and analyzing large amounts of RS imagery poses substantial challenges. Google Earth Engine (GEE) provides a scalable, cloud-based, geospatial retrieval and processing platform. GEE also provides access to the vast majority of freely available, public, multi-temporal RS data and offers free cloud-based computational power for geospatial data analysis. Artificial intelligence (AI) methods are a critical enabling technology to automating the interpretation of RS imagery, particularly on object-based domains, so the integration of AI methods into GEE represents a promising path towards operationalizing automated RS-based monitoring programs. In this article, we provide a systematic review of relevant literature to identify recent research that incorporates AI methods in GEE. We then discuss some of the major challenges of integrating GEE and AI and identify several priorities for future research. We developed an interactive web application designed to allow readers to intuitively and dynamically review the publications included in this literature review.

UAV-Based Multitemporal Remote Sensing Surveys of Volcano Unstable Flanks: A Case Study from Stromboli

UAV-based photogrammetry is becoming increasingly popular even in application fields that, until recently, were deemed unsuitable for this technique. Depending on the characteristics of the investigated scenario, the generation of three-dimensional (3D) topographic models may in fact be affected by significant inaccuracies unless site-specific adaptations are implemented into the data collection and processing routines. In this paper, an ad hoc procedure to exploit high-resolution aerial photogrammetry for the multitemporal analysis of the unstable Sciara del Fuoco (SdF) slope at Stromboli Island (Italy) is presented. Use of the technique is inherently problematic because of the homogeneous aspect of the gray ash slope, which prevents a straightforward identification of match points in continuous frames. Moreover, due to site accessibility restrictions enforced by local authorities after the volcanic paroxysm in July 2019, Ground Control Points (GCPs) cannot be positioned to constrain georeferencing. Therefore, all 3D point clouds were georeferenced using GCPs acquired in a 2019 (pre-paroxysm) survey, together with stable Virtual Ground Control Points (VGCPs) belonging to a LiDAR survey carried out in 2012. Alignment refinement was then performed by means of an iterative algorithm based on the closest points. The procedure succeeded in correctly georeferencing six high-resolution point clouds acquired from April 2017 to July 2021, whose time-focused analysis made it possible to track several geomorphological structures associated with the continued volcanic activity. The procedure can be further extended to smaller-scale analyses such as the estimation of locally eroded/accumulated volumes and pave the way for rapid UAV-based georeferenced surveys in emergency conditions at the SdF.

Mapping Fire Susceptibility in the Brazilian Amazon Forests Using Multitemporal Remote Sensing and Time-Varying Unsupervised Anomaly Detection

The economic and environmental impacts of wildfires have leveraged the development of new technologies to prevent and reduce the occurrence of these devastating events. Indeed, identifying and mapping fire-susceptible areas arise as critical tasks, not only to pave the way for rapid responses to attenuate the fire spreading, but also to support emergency evacuation plans for the families affected by fire-related tragedies. Aiming at simultaneously mapping and measuring the risk of fires in the forest areas of Brazil’s Amazon, in this paper we combine multitemporal remote sensing, derivative spectral indices, and anomaly detection into a fully unsupervised methodology. We focus our analysis on recent forest fire events that occurred in the Brazilian Amazon by exploring multitemporal images acquired by both Landsat-8 Operational Land Imager and Modis sensors. We experimentally confirm that the current methodology is capable of predicting fire outbreaks immediately at posterior instants, which attests to the operational performance and applicability of our approach to preventing and mitigating the impact of fires in Brazilian forest regions.

The Impact of Central Heating on the Urban Thermal Environment Based on Multi-Temporal Remote Sensing Images

Research on the impact of anthropogenic heat discharge in a thermal environment is significant in climate change research. Central heating is more common in the winter in Northeast China as an anthropogenic heat. This study investigates the impact of central heating on the thermal environment in Shenyang, Changchun, and Harbin based on multi-temporal land surface temperature retrieval from remote sensing. An equivalent heat island index method was proposed to overcome the problem of the method based on a single-phase image, which cannot evaluate all the central heating season changes. The method improves the comprehensiveness of a thermal environment evaluation by considering the long-term heat accumulation. The results indicated a significant increase in equivalent heat island areas at night with 22.1%, 17.3%, and 19.5% over Shenyang, Changchun, and Harbin. The increase was significantly positively correlated with the central heating supply (with an R-value of 0.89 for Shenyang, 0.93 for Changchun, and 0.86 for Harbin; p < 0.05). The impact of central heating has a more significant effect than the air temperature. The results provide a reference for future studies of urban thermal environment changes.

Recognition of the Bare Soil Using Deep Machine Learning Methods to Create Maps of Arable Soil Degradation Based on the Analysis of Multi-Temporal Remote Sensing Data

The detection of degraded soil distribution areas is an urgent task. It is difficult and very time consuming to solve this problem using ground methods. The modeling of degradation processes based on digital elevation models makes it possible to construct maps of potential degradation, which may differ from the actual spatial distribution of degradation. The use of remote sensing data (RSD) for soil degradation detection is very widespread. Most often, vegetation indices (indicative botany) have been used for this purpose. In this paper, we propose a method for constructing soil maps based on a multi-temporal analysis of the bare soil surface (BSS). It is an alternative method to the use of vegetation indices. The detection of the bare soil surface was carried out using the spectral neighborhood of the soil line (SNSL) technology. For the automatic recognition of BSS on each RSD image, computer vision based on deep machine learning (neural networks) was used. A dataset of 244 BSS distribution masks on 244 Landsat 4, 5, 7, and 8 scenes over 37 years was developed. Half of the dataset was used as a training sample (Landsat path/row 173/028). The other half was used as a test sample (Landsat path/row 174/027). Binary masks were sufficient for recognition. For each RSD pixel, value “1” was set when determining the BSS. In the absence of BSS, value “0” was set. The accuracy of the machine prediction of the presence of BSS was 75%. The detection of degradation was based on the average long-term spectral characteristics of the RED and NIR bands. The coefficient Cmean, which is the distance of the point with the average long-term values of RED and NIR from the origin of the spectral plane RED/NIR, was calculated as an integral characteristic of the mean long-term values. Higher long-term average values of spectral brightness served as indicators of the spread of soil degradation. To test the method of constructing soil degradation maps based on deep machine learning, an acceptance sample of 133 Landsat scenes of path/row 173/026 was used. On the territory of the acceptance sample, ground verifications of the maps of the coefficient Cmean were carried out. Ground verification showed that the values of this coefficient make it possible to estimate the content of organic matter in the plow horizon (R2 = 0.841) and the thickness of the humus horizon (R2 = 0.8599). In total, 80 soil pits were analyzed on an area of 649 ha on eight agricultural fields. Type I error (false positive) of degradation detection was 17.5%, and type II error (false negative) was 2.5%. During the determination of the presence of degradation by ground methods, 90% of the ground data coincided with the detection of degradation from RSD. Thus, the quality of machine learning for BSS recognition is sufficient for the construction of soil degradation maps. The SNSL technology allows us to create maps of soil degradation based on the long-term average spectral characteristics of the BSS.

Predictive Soil Mapping in the Boreal Plains of Northern Alberta Using Multi-Temporal Remote Sensing Data and Terrain Derivatives

Predictive Soil Mapping in the Boreal Plains of Northern Alberta Using Multi-Temporal Remote Sensing Data and Terrain Derivatives

Automatic Relative Radiometric Normalization of Bi-Temporal Satellite Images Using a Coarse-to-Fine Pseudo-Invariant Features Selection and Fuzzy Integral Fusion Strategies

Relative radiometric normalization (RRN) is important for pre-processing and analyzing multitemporal remote sensing (RS) images. Multitemporal RS images usually include different land use/land cover (LULC) types; therefore, considering an identical linear relationship during RRN modeling may result in potential errors in the RRN results. To resolve this issue, we proposed a new automatic RRN technique that efficiently selects the clustered pseudo-invariant features (PIFs) through a coarse-to-fine strategy and uses them in a fusion-based RRN modeling approach. In the coarse stage, an efficient difference index was first generated from the down-sampled reference and target images by combining the spectral correlation, spectral angle mapper (SAM), and Chebyshev distance. This index was then categorized into three groups of changed, unchanged, and uncertain classes using a fast multiple thresholding technique. In the fine stage, the subject image was first segmented into different clusters by the histogram-based fuzzy c-means (HFCM) algorithm. The optimal PIFs were then selected from unchanged and uncertain regions using each cluster’s bivariate joint distribution analysis. In the RRN modeling step, two normalized subject images were first produced using the robust linear regression (RLR) and cluster-wise-RLR (CRLR) methods based on the clustered PIFs. Finally, the normalized images were fused using the Choquet fuzzy integral fusion strategy for overwhelming the discontinuity between clusters in the final results and keeping the radiometric rectification optimal. Several experiments were implemented on four different bi-temporal satellite images and a simulated dataset to demonstrate the efficiency of the proposed method. The results showed that the proposed method yielded superior RRN results and outperformed other considered well-known RRN algorithms in terms of both accuracy level and execution time.

Integrated use of multi-temporal multi-sensor and multiscale Remote Sensing data for the understanding of archaeological contexts: the case study of Metaponto, Basilicata.

Abstract This paper is focused on the archaeological area of Metaponto (Mexomov-nov) and its territory, located in southern Italy. The area played an important role for the agricultural economy and the traffic of goods and people, from the south of Italy towards the central regions, starting from the Neolithic period, and reaching the zenith with the Greek polis of Metaponto and its hinterland. The site is herein analyzed through an integrated use of several Earth observation and remote sensing technologies and ancillary data produced over the years by archaeologists and scholars. The aim was to identify new buried elements of archaeological interest, for the reconstruction of the historical-archaeological landscape. Through the combined use of optical and radar satellite images, high-resolution images obtained by Unmanned Aerial System (visible, multispectral, and thermal infrared), geophysical data, and archival data, it was possible to deepen the knowledge of the area, in particular the “Castrum” area, identifying new buried evidence (structures, roads, and elements of the ancient landscape).