Search

Abstract Land Use and Land Cover (LULC) maps are important tools for environmental planning and social-ecological modeling, as they provide critical information for evaluating risks, managing natural resources, and facilitating effective decision-making. This study aimed to generate a very high spatial resolution (0.5 m) and detailed (21 classes) LULC map for the greater Mariño watershed (Peru) in 2019, using the MORINGA processing chain. This new method for LULC mapping consisted in a supervised object-based LULC classification, using the random forest algorithm along with multi-sensor satellite imagery from which spectral and textural predictors were derived (a very high spatial resolution Pléiades image and a time serie of high spatial resolution Sentinel-2 images). The random forest classifier showed a very good performance and the LULC map was further improved through additional post-treatment steps that included cross-checking with external GIS data sources and manual correction using photointerpretation, resulting in a more accurate and reliable map. The final LULC provides new information for environmental management and monitoring in the greater Mariño watershed. With this study we contribute to the efforts to develop standardized and replicable methodologies for high-resolution and high-accuracy LULC mapping, which is crucial for informed decision-making and conservation strategies.

Nowadays, satellite image time series (SITS) are commonly employed to derive land-cover maps (LCM) to support decision makers in a variety of land management applications. In the most general workflow, the production of LCM strongly relies on available GT data to train supervised machine learning models. Unfortunately, these data are not always available due to time-consuming and costly field campaigns. In this scenario, the possibility to transfer a model learnt on a particular year (source domain) to a successive period of time (target domain), over the same study area, can save time and money. Such a kind of model transfer is challenging due to different acquisition conditions affecting each time period, thus resulting in possible distribution shifts between source and target domains. In the general field of machine learning, unsupervised domain adaptation (UDA) approaches are well suited to cope with the learning of models under distribution shifts between source and target domains. While widely explored in the general computer vision field, they are still underinvestigated for SITS-based land-cover mapping, especially for the temporal transfer scenario. With the aim to cope with this scenario in the context of SITS-based land-cover mapping, here we propose spatially aligned domain-adversarial neural network, a framework that combines both adversarial learning and self-training to transfer a classification model from a time period (year) to a successive one on a specific study area. Experimental assessment on a study area located in Burkina Faso characterized by challenging operational constraints demonstrates the significance of our proposal. The obtained results have shown that our proposal outperforms all the UDA competing methods by 7 to 12 points of F1-score across three different transfer tasks.

Non-active agricultural land (NAAL) mapping in West Africa is essential to accurately assess agricultural systems and its contribution to food security and agro-ecological sustainability of current practices, and yet the available mapping methodologies are not adapted to the environmental and cropping conditions encountered when addressing tropical smallholder agriculture. In this study we present a strategy that makes use of Sentinel-2 image time series, CHIRPS monthly rainfall data and multiple years of in-situ data obtained from the JECAM database to map NAAL in a Soudanian site in Burkina Faso (Koumbia) between the years 2016 and 2021. In a first step we generated annual land use maps in four broad classes (managed, unmanaged, evergreen and non-vegetated) to detect fields being actively cultivated in a given year, and in a second step, we used these annual land use maps to differentiate non-active agricultural land by identifying shifts from one year to another. For the validation part, we analyzed the sensitivity of classification accuracy to in-situ data pre-processing by building 5 experimental validation data sets. The unmanaged classes F1-scores of the land use maps ranged between 0.86 and 0.98, depending on the year, whereas NAAL classes F1-scores ranged from 0.75 to 0.92 when validated against the most restrictive data set (pixels with no missing reference data for the period considered). NAAL represents between 7% to 14% of the study site cropland depending on the year. The higher class probabilities are in areas where data was available, whereas the low probabilities are localized and linked to transition areas on the outskirts of the department. Our results indicate that a multi-annual approach can allow NAAL mapping under challenging environments, yet efforts are to be made to develop more cost-efficient unsupervised solutions.

Abstract Background Aberrant salience is a well-known construct associated with the development and maintenance of psychotic symptoms in schizophrenia. However, only a few studies have investigated aberrance salience as a trait, with no study investigating the association between the five aberrant salience domains and psychotic symptoms. We aimed to explore the role of aberrant salience and its domains on psychotic dimensions in both clinically remitted and non-remitted patients. Methods A sample of 102 patients diagnosed with schizophrenia spectrum disorders was divided according to the Positive and Negative Syndrome Scale (PANSS) remission criteria into two groups: remitted and non-remitted. Differences regarding psychotic symptomatology assessed by the PANSS and aberrant salience measured by the Aberrant Salience Inventory (ASI) were explored. Finally, a correlation analysis between the PANSS and the ASI was run. Results Significantly higher ASI scores were evident among non-remitted patients. Positive symptoms (i.e. delusions, conceptual disorganization, and hallucinatory behaviour) and general psychopathology (i.e. postural mannerisms, unusual thought content) were correlated to the aberrant salience subscales ‘sharpening of senses’, ‘heightened emotionality’ and ‘heightened cognition’ and with the ASI total score. Significant correlations emerged between negative symptoms (blunted affect and social withdrawal) and ‘heightened cognition'. Finally, lack of spontaneity of conversation was related to the subscales ‘heightened emotionality’ and ‘heightened cognition’, as well as to the ASI total score. Conclusions These preliminary results support the hypothesis of an association between aberrant salience and psychotic symptoms in schizophrenia. Further research is needed, especially into the mechanisms underlying salience processing, in addition to social and environmental factors and cognitive variables.

Satellite image time series (SITS) collected by modern Earth Observation (EO) systems represent a valuable source of information that supports several tasks related to the monitoring of the Earth surface dynamics over large areas. A main challenge is then to design methods able to leverage the complementarity between the temporal dynamics and the spatial patterns that characterize these data structures. Focusing on land cover classification (or mapping) tasks, the majority of approaches dealing with SITS data only considers the temporal dimension, while the integration of the spatial context is frequently neglected. In this work, we propose an attentive spatial temporal graph convolutional neural network that exploits both spatial and temporal dimensions in SITS. Despite the fact that this neural network model is well suited to deal with spatio-temporal information, this is the first work that considers it for the analysis of SITS data. Experiments are conducted on two study areas characterized by different land cover landscapes and real-world operational constraints (i.e., limited labeled data due to acquisition costs). The results show that our model consistently outperforms all the competing methods obtaining a performance gain, in terms of F-Measure, of at least 5 points with respect to the best competing approaches on both benchmarks.

Extensive research studies have been conducted in recent years to exploit the complementarity among multisensor (or multimodal) remote sensing data for prominent applications such as land cover mapping. In order to make a step further with respect to previous studies, which investigate multitemporal SAR and optical data or multitemporal/multiscale optical combinations, here, we propose a deep learning framework that simultaneously integrates all these input sources, specifically multitemporal SAR/optical data and fine-scale optical information at their native temporal and spatial resolutions. Our proposal relies on a patch-based multibranch convolutional neural network (CNN) that exploits different per-source encoders to deal with the specificity of the input signals. In addition, we introduce a new self-distillation strategy to boost the per-source analyses and exploit the interplay among the different input sources. This new strategy leverages the final prediction of the multisource framework to guide the learning of the per-source CNN encoders supporting the network to learn from itself. Experiments are carried out on two real-world benchmarks, namely, the Reunion island (a French overseas department) and the Dordogne study site (a southwest department in France), where the annotated reference data were collected under operational constraints (sparsely annotated ground-truth data). Obtained results providing an overall classification accuracy of about 94% (respectively, 88%) on the Reunion island (respectively, the Dordogne) study site highlight the effectiveness of our framework based on CNNs and self-distillation to combine heterogeneous multisensor remote sensing data and confirm the benefit of multimodal analysis for downstream tasks such as land cover mapping.

The unprecedented possibility to acquire high resolution Satellite Image Time Series (SITS) data is opening new opportunities to monitor the different aspects of the Earth Surface but, at the same time, it is raising up new challenges in term of suitable methods to analyze and exploit such huge amount of rich image data. One of the main tasks associated to SITS data analysis is related to land cover mapping. Due to operational constraints, the collected label information is often limited in volume and obtained at coarse granularity level carrying out inexact and weak knowledge that can affect the whole process. To cope with such issues, in the context of object-based SITS land cover mapping, we propose a new deep learning framework, named TASSEL (aTtentive weAkly Supervised Satellite image time sEries cLassifier), to deal with the weak supervision provided by the coarse granularity labels. Our framework exploits the multifaceted information conveyed by the object-based representation considering object components instead of aggregated object statistics. Furthermore, our framework also produces an additional outcome that supports the model interpretability. Quantitative and qualitative experimental evaluations are carried out on two real-world scenarios. Results indicate that not only TASSEL outperforms the competing approaches in terms of predictive performances, but it also produces valuable extra information that can be practically exploited to interpret model decisions.

Agroforestry plays a pivotal role for Sahelian communities by allowing simultaneous improvement of food security and conservation of natural ecosystems and their biodiversity. However, agroforestry systems (AFSs) are particularly heterogeneous in sub-Saharan Africa due to small to very small fields, a large variety of agricultural practices and a diversity of parkland compositions and configurations. This makes spatial sampling processes very important but problematic in terms of representativeness of the landscape heterogeneity to allow an effective study of Sahelian AFSs. In this paper, we proposed, tested and assessed a methodological approach for landscape sampling, mapping and characterization while considering the different types of spatial heterogeneity in complex landscapes, such as Sahelian AFSs. Several complementary methods were combined on the basis of a priori knowledge of agroforestry landscape functioning using multisource data, remote sensing methods, and statistical and spatial analyses applied to landscape ecology. First, the landscape heterogeneity was stratified and used to design two weighted, stratified sampling plans for field surveys of tree species and land use/land cover types. Then, with multisource satellite images together with collected field data, the agroforestry systems were mapped, with a satisfactory accuracy of 85.12% and a Kappa index of 0.81. Finally, we used landscape metrics and diversity indices derived from AFS mapping and the tree species inventory to analyze the diversity of the studied AFS located in the Senegalese Peanut Basin. The results of the analysis evidenced the compositional, configurational and functional heterogeneity found in the study area. This allowed us to demonstrate the ability of the sampling strategy proposed in this paper to capture the various types of heterogeneity in agricultural landscapes. We also showed by implementing the method that it can be used for (i) tree biodiversity analysis, (ii) mapping and (iii) characterization of a complex AFS in sub-Saharan Africa.

Background: Binge eating disorder (BED) is clinically relevant by virtue of the global impairment, poor quality of life, and increased overall medical morbidity. The high comorbidity with psychiatric disorders, particularly depression, has received attention as a possible mediator of the poor outcome. Further, BED and depression share cognitive dysfunctions. This naturalistic and uncontrolled pilot study aimed at evaluating the efficacy of vortioxetine (VTX) on depressive symptoms in patients with BED, secondly the efficacy in improving a broad array of executive functions, and third to explore the effect on eating behavior and body weight.Methods: This pilot study involved 30 patients with BED and comorbid MDD, treated with VTX for 24 weeks. Assessments were run at baseline (t0), 4 (t1), 8 (t2), 12 (t3), and 24 (t4) weeks. Changes in depressive symptoms (HDRS and BDI), executive functions, eating behaviors (binge frequency and severity, night eating, food addiction), and body weight were estimated after treatment with VTX through GLM.Results: Significant improvements emerged after treatment with VTX in: depression (HDRS p < 0.001; BDI p = 0.002) regardless the dose of VTX and first diagnosis (BED/MDD), working memory (RAVLT acquisition p = 0.01, delay recall p < 0.001, RCFT percentage of recall p = 0.01, and Attentional Matrices p = 0.05), binge days frequency (p < 0.001), binge eating severity (BES p < 0.001), night eating (p = 0.001), food addiction (YFAS 2.0 p = 0.039), and body weight (p = 0.039). The improvement in depressive symptoms was associated with the concurrent improvement in night eating as assessed by the I-NEQ.Conclusions: VTX can be a valid therapeutic choice for patients with BED with comorbid depression in controlling the depressive symptoms, working memory, and eating behavior. Indeed, by acting on affective symptoms, neurocognitive functioning, and eating behaviors, it confirms the results already obtained with VTX in other disorders, expanding them to BED.

The adoption of new cropping practices such as integrated Crop-Livestock systems (iCL) aims at improving the land use sustainability of the agricultural sector in the Brazilian Amazon. The emergence of such integrated systems, based on crop and pasture rotations over and within years, challenges the remote sensing community who needs to implement accurate and efficient methods to process satellite image time series (SITS) in order to come up with a monitoring protocol. These methods generally include a SITS preprocessing step which can be time consuming. The aim of this study is to assess the importance of preprocessing operations such as temporal smoothing and computation of phenological metrics on the mapping of main cropping systems (i.e. pasture, single cropping, double cropping and iCL), with a special emphasis on the iCL class. The study area is located in the state of Mato Grosso, an important producer of agriculture commodities located in the Southern Brazilian Amazon. SITS were composed of a set of 16-day composites of MODIS Vegetation Indices (MOD13Q1 product) covering a one year period between 2014 and 2015. Two widely used classifiers, i.e. Random Forest (RF) and Support Vector Machine (SVM), were tested using five data sets issued from a same SITS but with different preprocessing levels: (i) raw NDVI; (ii) raw NDVI + raw EVI; (iii) smoothed NDVI; (iv) NDVI-derived phenometrics; (v) raw NDVI + phenometrics. Both RF and SVM classification results showed that the “raw NDVI + raw EVI” data set achieved the highest performance (RF OA = 0.96, RF Kappa = 0.94, SVM OA = 0.95, SVM Kappa = 0.93), followed closely by the “raw NDVI” and the “raw NDVI + phenometrics” datasets. The “NDVI-derived phenometrics” alone achieved the lowest accuracies (RF OA = 0.58 and SVM OA = 0.66). Considering that the implementation of preprocessing steps is computationally expensive and does not provide significant gains in terms of classification accuracy, we recommend to use raw vegetation indices for mapping cropping practices in Mato Grosso, including the integrated Crop-Livestock systems.

Due to different combinations of agriculture, livestock and forestry managed by rotation, succession and intercropping practices, integrated agriculture production systems such as integrated crop–livestock systems (iCL) constitute a very complex target and a challenge for automatic mapping of cropping practices based on remote sensing data. The overall objective of this study was to develop a classification strategy for the annual mapping of integrated Crop–Livestock systems (iCL) at a regional scale. This strategy was designed and tested in the six agro-climatic regions of Mato Grosso, the largest Brazilian soybean producer state, using MODIS satellite time-series images acquired between 2012 and 2019, ground data with heterogeneous distribution in space and time and a Random Forest classifier. The results showed that: 1. the use of unbalanced training samples with a class composition close to the real one was the right classifier training strategy; 2. the use of a single training database (pooling samples from different years and regions) to classify each region and year individually proved to be robust enough to provide similar classification accuracies in comparison to those based on the use of a database acquired for each region and for each year. The final hierarchical classification overall accuracy was 0.89 for Level 1, the cropping pattern level (single and double crops DC); 0.84 for Level 2, the DC category level (integrated system iCL soy-pasture/brachiaria, soy-cotton and soy-cereal); 0.77 for Level 3, the iCL level (iCL1 soy-pasture and iCL2 soy-pasture mixed with corn). The F-scores for DC, iCL and iCL1 cropping systems presented high accuracy (0.89, 0.85 and 0.84), while iCL2 was more difficult to classify (0.63). This approach will next be applied across the entire Brazilian soybean corridor, leading to an operational tool for monitoring the adoption of sustainable intensification practices recognized by Brazil’s Agriculture Low Carbon Plan (ABC PLAN).

Background and Objectives: Bipolar Disorder (BD) is a severe psychiatric disorder that worsens quality of life and functional impairment. Personality disorders (PDs), in particular Cluster B personality, have a high incidence among BD patients and is considered a poor prognostic factor. The study of this co-morbidity represents an important clinical and diagnostic challenge in psychiatry. Particularly, clinical overlap has been shown between antisocial personality disorder (ASPD) and BD that could worsen the course of both disorders. We aimed to detect the frequency of ASPD in bipolar patients with greater accuracy and the impact of ASPD on the clinical course of BD. Materials and Methods: A systematic literature search was conducted in PubMed, Embase, MEDLINE and the Cochrane Library through December 2020 without language or time restriction, according to PRISMA statement guidelines. Results: Initially, 3203 items were identified. After duplicates or irrelevant paper deletion, 17 studies met the inclusion criteria and were included in this review. ASPD was more frequent among BD patients, especially in BD type I. BD patients with ASPD as a comorbidity seemed to have early onset, higher number and more severe affective episodes, higher levels of aggressive and impulsive behaviors, suicidality and poor clinical outcome. ASPD symptoms in BD seem to be associated with a frequent comorbidity with addictive disorders (cocaine and alcohol) and criminal behaviors, probably due to a shared impulsivity core feature. Conclusions: Considering the shared symptoms such as impulsive and dangerous behaviors, in patients with only one disease, misdiagnosis is a common phenomenon due to the overlapping symptoms of ASPD and BD. It may be useful to recognize the co-occurrence of the disorders and better characterize the patient with ASPD and BD evaluating all dysfunctional aspects and their influence on core symptoms.

European satellite missions Sentinel-1 (S1) and Sentinel-2 (S2) provide at high spatial resolution and high revisit time, respectively, radar and optical images that support a wide range of Earth surface monitoring tasks, such as Land Use/Land Cover mapping. A long-standing challenge in the remote sensing community is about how to efficiently exploit multiple sources of information and leverage their complementarity, in order to obtain the most out of radar and optical data. In this work, we propose to deal with land cover mapping in an object-based image analysis (OBIA) setting via a deep learning framework designed to leverage the multi-source complementarity provided by radar and optical satellite image time series (SITS). The proposed architecture is based on an extension of Recurrent Neural Network (RNN) enriched via a modified attention mechanism capable to fit the specificity of SITS data. Our framework also integrates a pretraining strategy that allows to exploit specific domain knowledge, shaped as hierarchy over the set of land cover classes, to guide the model training. Thorough experimental evaluations, involving several competitive approaches were conducted on two study sites, namely the Reunion island and a part of the Senegalese groundnut basin. Classification results, 79% of global accuracy on the Reunion island and 90% on the Senegalese site, respectively, have demonstrated the suitability of the proposal.

High urbanization rates in cities lead to rapid changes in land uses, particularly in southern cities where population growth is fast. Urban and peri-urban agricultural land is often seen as available space for the city to expand, but at the same time, agricultural land provides many benefits to cities pertaining to food, employment, and eco-services. In this context, there is an urgent need to provide spatial information to support planning in complex urban systems. The challenge is to integrate analysis of agriculture and urban land-cover classes, and of their spatial and functional patterns. This paper takes up this challenge in Antananarivo (Madagascar), where agricultural plots and homes are interlocked and very small. It innovates by using a methodology already tested in rural settings, but never applied to urban environments. The key step of the analysis is to produce landscape zoning based on multisource satellite data to identify agri-urban functional areas within the city, and to explore their relationships. Our results demonstrate that the proposed classification method is well suited for mapping agriculture and urban land cover (overall accuracy = 76.56% for the 20 classes of level 3) in such a complex setting. The systemic analysis of urban agriculture patterns and functions can help policymakers and urban planners to design and build resilient cities.

Images provided by the ESA Sentinel-2 mission are rapidly becoming the main source of information for the entire remote sensing community, thanks to their unprecedented combination of spatial, spectral and temporal resolution, as well as their associated open access policy. Due to a sensor design trade-off, images are acquired (and delivered) at different spatial resolutions (10, 20 and 60 m) according to specific sets of wavelengths, with only the four visible and near infrared bands provided at the highest resolution (10 m). Although this is not a limiting factor in general, many applications seem to emerge in which the resolution enhancement of 20 m bands may be beneficial, motivating the development of specific super-resolution methods. In this work, we propose to leverage Convolutional Neural Networks (CNNs) to provide a fast, upscalable method for the single-sensor fusion of Sentinel-2 (S2) data, whose aim is to provide a 10 m super-resolution of the original 20 m bands. Experimental results demonstrate that the proposed solution can achieve better performance with respect to most of the state-of-the-art methods, including other deep learning based ones with a considerable saving of computational burden.

The use of Very High Spatial Resolution (VHSR) imagery in remote sensing applications is nowadays a current practice whenever fine-scale monitoring of the earth’s surface is concerned. VHSR Land Cover classification, in particular, is currently a well-established tool to support decisions in several domains, including urban monitoring, agriculture, biodiversity, and environmental assessment. Additionally, land cover classification can be employed to annotate VHSR imagery with the aim of retrieving spatial statistics or areas with similar land cover. Modern VHSR sensors provide data at multiple spatial and spectral resolutions, most commonly as a couple of a higher-resolution single-band panchromatic (PAN) and a coarser multispectral (MS) imagery. In the typical land cover classification workflow, the multi-resolution input is preprocessed to generate a single multispectral image at the highest resolution available by means of a pan-sharpening process. Recently, deep learning approaches have shown the advantages of avoiding data preprocessing by letting machine learning algorithms automatically transform input data to best fit the classification task. Following this rationale, we here propose a new deep learning architecture to jointly use PAN and MS imagery for a direct classification without any prior image sharpening or resampling process. Our method, namely M u l t i R e s o L C C , consists of a two-branch end-to-end network which extracts features from each source at their native resolution and lately combine them to perform land cover classification at the PAN resolution. Experiments are carried out on two real-world scenarios over large areas with contrasted land cover characteristics. The experimental results underline the quality of our method while the characteristics of the proposed scenarios underline the applicability and the generality of our strategy in operational settings.

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.