Explore the vast range of titles available.

This paper presents an innovative multisensor, multitemporal machine-learning approach using remote sensing big data for the detection of archaeological mounds in Cholistan (Pakistan). The Cholistan Desert presents one of the largest concentrations of Indus Civilization sites (from ca. 3300 to 1500 BC). Cholistan has figured prominently in theories about changes in water availability, the rise and decline of the Indus Civilization, and the transformation of fertile monsoonal alluvial plains into an extremely arid margin. This paper implements a multisensor, multitemporal machine-learning approach for the remote detection of archaeological mounds. A classifier algorithm that employs a large-scale collection of synthetic-aperture radar and multispectral images has been implemented in Google Earth Engine, resulting in an accurate probability map for mound-like signatures across an area that covers ca. 36,000 km². The results show that the area presents many more archaeological mounds than previously recorded, extending south and east into the desert, which has major implications for understanding the archaeological significance of the region. The detection of small (<5 ha) to large mounds (>30 ha) suggests that there were continuous shifts in settlement location. These shifts are likely to reflect responses to a dynamic and changing hydrological network and the influence of the progressive northward advance of the desert in a long-term process that culminated in the abandonment of much of the settled area during the Late Harappan period.

The exploitation of Earth observation satellite images acquired by optical instruments requires an automatic and accurate cloud detection. Multitemporal approaches to cloud detection are usually more powerful than their single scene counterparts since the presence of clouds varies greatly from one acquisition to another whereas surface can be assumed stationary in a broad sense. However, two practical limitations usually hamper their operational use: the access to the complete satellite image archive and the required computational power. This work presents a cloud detection and removal methodology implemented in the Google Earth Engine (GEE) cloud computing platform in order to meet these requirements. The proposed methodology is tested for the Landsat-8 mission over a large collection of manually labeled cloud masks from the Biome dataset. The quantitative results show state-of-the-art performance compared with mono-temporal standard approaches, such as FMask and ACCA algorithms, yielding improvements between 4–5% in classification accuracy and 3–10% in commission errors. The algorithm implementation within the Google Earth Engine and the generated cloud masks for all test images are released for interested readers.

James, D.; Collin, A.; Bouet, A.; Perette, M.; Dimeglio, T.; Hervouet, G.; Durozier, T.; Duthion, G., and Lebas, J-F., 2024. Multi-temporal drone mapping of coastal ecosystems in restoration: Seagrass, salt marsh, and dune. In: Phillips, M.R.; Al-Naemi, S., and Duarte, C.M. (eds.), Coastlines under Global Change: Proceedings from the International Coastal Symposium (ICS) 2024 (Doha, Qatar). Journal of Coastal Research, Special Issue No. 113, pp. 524-528. Charlotte (North Carolina), ISSN 0749-0208. Ecotones at the land-sea interface provide valuable geo-ecological benefits, providing services such as biodiversity support, coastal protection, and environmental amenities. In temperate sandy-muddy regions, blue carbon ecosystems (seagrass meadows, salt marshes) store more carbon than temperate or tropical forests. Temperate sandy areas, with dunes and vegetation, trap sediment and significantly limit coastal erosion. Recognizing their importance in the face of global change, these ecosystems are being protected and restored. In Europe, coastal development has fragmented these ecosystems into smaller patches, making them difficult to map by satellite or aircraft. Drone imagery is now revealing their spatial patterns and processes, with the potential for ultra-high resolution (UHR) pixel size, although it's high temporal resolution remains a niche in research. The study addresses this issue by generating time series of UHR classifications for three ecosystems under restoration: seagrass, salt marsh, and dune. Three coastal sites in northern Brittany were selected: a subtidal seagrass meadow (for anchoring and fishing), a restricted salt marsh (an old polder reconnected to the sea), and a dune dealing with coastal infrastructure issues (road). Aerial drones with red-green-blue sensors flew over these sites annually: since 2021 for the seagrass (8 times), since 2020 for the salt marsh (8 times), and since 2022 for the dune (5 times). Training and validation data were located on identical areas on overlaid orthomosaics, and two pixel-oriented supervised classification algorithms were tested: probabilistic and fast Maximum Likelihood (ML), and decision and efficient Random Forest (RF). Overall accuracies from confusion matrices were compared for each algorithm. For the seagrass meadow, results ranged from 78.33% to 87.18% (ML) and from 86.06% to 93.10% (RF); for the salt marsh, variations were between 71.61% to 95.32% (ML) and 88.69% to 98.59% (RF); for the sand dune, results ranged from 90.04% to 95.5% (ML) and from 93.8% to 96.06% (RF). Regardless of the geo-ecosystem, the RF algorithm consistently outperformed the ML algorithm in mapping.

The Synthetic Aperture Radar (SAR) time series allows describing the rice phenological cycle by the backscattering time signature. Therefore, the advent of the Copernicus Sentinel-1 program expands studies of radar data (C-band) for rice monitoring at regional scales, due to the high temporal resolution and free data distribution. Recurrent Neural Network (RNN) model has reached state-of-the-art in the pattern recognition of time-sequenced data, obtaining a significant advantage at crop classification on the remote sensing images. One of the most used approaches in the RNN model is the Long Short-Term Memory (LSTM) model and its improvements, such as Bidirectional LSTM (Bi-LSTM). Bi-LSTM models are more effective as their output depends on the previous and the next segment, in contrast to the unidirectional LSTM models. The present research aims to map rice crops from Sentinel-1 time series (band C) using LSTM and Bi-LSTM models in West Rio Grande do Sul (Brazil). We compared the results with traditional Machine Learning techniques: Support Vector Machines (SVM), Random Forest (RF), k-Nearest Neighbors (k-NN), and Normal Bayes (NB). The developed methodology can be subdivided into the following steps: (a) acquisition of the Sentinel time series over two years; (b) data pre-processing and minimizing noise from 3D spatial-temporal filters and smoothing with Savitzky-Golay filter; (c) time series classification procedures; (d) accuracy analysis and comparison among the methods. The results show high overall accuracy and Kappa (>97% for all methods and metrics). Bi-LSTM was the best model, presenting statistical differences in the McNemar test with a significance of 0.05. However, LSTM and Traditional Machine Learning models also achieved high accuracy values. The study establishes an adequate methodology for mapping the rice crops in West Rio Grande do Sul.

Land cover and its change are crucial for many environmental applications. This study focuses on the land cover classification and change detection with multitemporal and multispectral Sentinel-2 satellite data. To address the challenging land cover change detection task, we rely on two different deep learning architectures and selected pre-processing steps. For example, we define an excluded class and deal with temporal water shoreline changes in the pre-processing. We employ a fully convolutional neural network (FCN), and we combine the FCN with long short-term memory (LSTM) networks. The FCN can only handle monotemporal input data, while the FCN combined with LSTM can use sequential information (multitemporal). Besides, we provided fixed and variable sequences as training sequences for the combined FCN and LSTM approach. The former refers to using six defined satellite images, while the latter consists of image sequences from an extended training pool of ten images. Further, we propose measures for the robustness concerning the selection of Sentinel-2 image data as evaluation metrics. We can distinguish between actual land cover changes and misclassifications of the deep learning approaches with these metrics. According to the provided metrics, both multitemporal LSTM approaches outperform the monotemporal FCN approach, about 3 to 5 percentage points (p.p.). The LSTM approach trained on the variable sequences detects 3 p.p. more land cover changes than the LSTM approach trained on the fixed sequences. Besides, applying our selected pre-processing improves the water classification and avoids reducing the dataset effectively by 17.6%. The presented LSTM approaches can be modified to provide applicability for a variable number of image sequences since we published the code of the deep learning models. The Sentinel-2 data and the ground truth are also freely available.

On 24 August 2016, the M 6.2 Amatrice earthquake struck central Italy, well-known as a seismically active region, causing considerable damage to buildings in the town of Amatrice and the surrounding area. Damage from this earthquake was assessed quantitatively by means of multitemporal synthetic aperture radar (SAR) coherence and SAR intensity methods using dual-polarized SAR data obtained from the Sentinel-1 (VV, VH) and ALOS-2 (HH, HV) satellites. We developed linear discriminant functions based on three items: (1) the differential coherence values; (2) the differential backscattering intensity values of pre- and post-event images; and (3) a binary damage map of the optical pre- and post-event imagery. The accuracy of the proposed model was 84% for the Sentinel-1 data and 76% for the ALOS-2 data. The damage proxy maps deduced from the linear discriminant functions can be useful in the parcel-by-parcel assessment of building damage and development of spatial models for the allocation of urban search and rescue operations.

Satellite images provide an accurate, continuous, and synoptic view of seamless global extent. Within the fields of remote sensing and image processing, land surface change detection (CD) has been amongst the most discussed topics. This article reviews advances in bitemporal and multitemporal two-dimensional CD with a focus on multispectral images. In addition, it reviews some CD techniques used for synthetic aperture radar (SAR). The importance of data selection and preprocessing for CD provides a starting point for the discussion. CD techniques are, then, grouped based on the change analysis products they can generate to assist users in identifying suitable procedures for their applications. The discussion allows users to estimate the resources needed for analysis and interpretation, while selecting the most suitable technique for generating the desired information such as binary changes, direction or magnitude of changes, “from-to” information of changes, probability of changes, temporal pattern, and prediction of changes. The review shows that essential and innovative improvements are being made in analytical processes for multispectral images. Advantages, limitations, challenges, and opportunities are identified for understanding the context of improvements, and this will guide the future development of bitemporal and multitemporal CD methods and techniques for understanding land cover dynamics.

The rapid advancement of remote sensing technology has significantly enhanced the temporal resolution of remote sensing data. Multitemporal remote sensing image classification can extract richer spatiotemporal features. However, this also presents the challenge of mining massive data features. In response to this challenge, deep learning methods have become prevalent in machine learning and have been widely applied in remote sensing due to their ability to handle large datasets. The combination of remote sensing classification and deep learning has become a trend and has developed rapidly in recent years. However, there is a lack of summary and discussion on the research status and trends in multitemporal images. This review retrieved and screened 170 papers and proposed a research framework for this field. It includes retrieval statistics from existing research, preparation of multitemporal datasets, sample acquisition, an overview of typical models, and a discussion of application status. Finally, this paper discusses current problems and puts forward prospects for the future from three directions: adaptability between deep learning models and multitemporal classification, prospects for high-resolution image applications, and large-scale monitoring and model generalization. The aim is to help readers quickly understand the research process and application status of this field.

Studies designed to discriminate different successional forest stages play a strategic role in forest management, forest policy and environmental conservation in tropical environments. The discrimination of different successional forest stages is still a challenge due to the spectral similarity among the concerned classes. Considering this, the objective of this paper was to investigate the performance of Sentinel-2 and Landsat-8 data for discriminating different successional forest stages of a patch located in a subtropical portion of the Atlantic Rain Forest in Southern Brazil with the aid of two machine learning algorithms and relying on the use of spectral reflectance data selected over two seasons and attributes thereof derived. Random Forest (RF) and Support Vector Machine (SVM) were used as classifiers with different subsets of predictor variables (multitemporal spectral reflectance, textural metrics and vegetation indices). All the experiments reached satisfactory results, with Kappa indices varying between 0.9, with Landsat-8 spectral reflectance alone and the SVM algorithm, and 0.98, with Sentinel-2 spectral reflectance alone also associated with the SVM algorithm. The Landsat-8 data had a significant increase in accuracy with the inclusion of other predictor variables in the classification process besides the pure spectral reflectance bands. The classification methods SVM and RF had similar performances in general. As to the RF method, the texture mean of the red-edge and SWIR bands were considered the most important ranked attributes for the classification of Sentinel-2 data, while attributes resulting from multitemporal bands, textural metrics of SWIR bands and vegetation indices were the most important ones in the Landsat-8 data classification.

Sensitivity to weather conditions, and specially to clouds, is a severe limiting factor to the use of optical remote sensing for Earth monitoring applications. A possible alternative is to benefit from weather-insensitive synthetic aperture radar (SAR) images. In many real-world applications, critical decisions are made based on some informative optical or radar features related to items such as water, vegetation or soil. Under cloudy conditions, however, optical-based features are not available, and they are commonly reconstructed through linear interpolation between data available at temporally-close time instants. In this work, we propose to estimate missing optical features through data fusion and deep-learning. Several sources of information are taken into account—optical sequences, SAR sequences, digital elevation model—so as to exploit both temporal and cross-sensor dependencies. Based on these data and a tiny cloud-free fraction of the target image, a compact convolutional neural network (CNN) is trained to perform the desired estimation. To validate the proposed approach, we focus on the estimation of the normalized difference vegetation index (NDVI), using coupled Sentinel-1 and Sentinel-2 time-series acquired over an agricultural region of Burkina Faso from May–November 2016. Several fusion schemes are considered, causal and non-causal, single-sensor or joint-sensor, corresponding to different operating conditions. Experimental results are very promising, showing a significant gain over baseline methods according to all performance indicators.