Semi-supervised water tank detection to support vector control of emerging infectious diseases transmitted by Aedes Aegypti

Geo-spatial Information Science

OpenStreetMap (OSM) is a dataset in constant change and this dynamic needs to be better understood. Based on 12-year time series of seven OSM data contribution activities extracted from 20 large cities worldwide, we investigate the temporal dynamic of OSM data production, more specifically, the auto- and cross-correlation, temporal trend, and annual seasonality of these activities. Furthermore, we evaluate and compare nine different temporal regression methods for forecasting such activities in horizons of 1–4 weeks. Several insights could be obtained from our analyses, including that the contribution activities tend to grown linearly in a moderate intra-annual cycle. Also, the performance of the temporal forecasting methods shows that they yield in general more accurate estimations of future contribution activities than a baseline metric, i.e. the arithmetic average of recent previous observations. In particular, the …

arXiv preprint arXiv:2404.04942

The emergence of the COVID-19 pandemic, followed by policy measures to combat the virus, evoked public protest movements world-wide. These movements emerged through virtual social networks as well as local protest gatherings. Prior research has studied such movements solely in the virtual space through social network analysis, thereby disregarding the role of local interaction for protest. This study, however, recognizes the importance of the geo-spatial dimension in protest movements. We therefore introduce a large-scale spatial-social network analysis of a georeferenced Twitter user network to understand the regional connections and transnational influences of the Austrian COVID-19 protest movement through the social network. Our findings reveal that the virtual network is distinctly structured along geographic and linguistic boundaries. We further find that the movement is clearly organized along national protest communities. These results highlight the importance of regional and local influencing factors over the impact of transnational influences for the protest movement.

arXiv preprint arXiv:2401.04218

We present a benchmark for assessing the capability of Large Language Models (LLMs) to discern intercardinal directions between geographic locations and apply it to three prominent LLMs: GPT-3.5, GPT-4, and Llama-2. This benchmark specifically evaluates whether LLMs exhibit a hierarchical spatial bias similar to humans, where judgments about individual locations' spatial relationships are influenced by the perceived relationships of the larger groups that contain them. To investigate this, we formulated 14 questions focusing on well-known American cities. Seven questions were designed to challenge the LLMs with scenarios potentially influenced by the orientation of larger geographical units, such as states or countries, while the remaining seven targeted locations less susceptible to such hierarchical categorization. Among the tested models, GPT-4 exhibited superior performance with 55.3% accuracy, followed by GPT-3.5 at 47.3%, and Llama-2 at 44.7%. The models showed significantly reduced accuracy on tasks with suspected hierarchical bias. For example, GPT-4's accuracy dropped to 32.9% on these tasks, compared to 85.7% on others. Despite these inaccuracies, the models identified the nearest cardinal direction in most cases, suggesting associative learning, embodying human-like misconceptions. We discuss the potential of text-based data representing geographic relationships directly to improve the spatial reasoning capabilities of LLMs.

Information

With the vast amount of social media posts available online, topic modeling and sentiment analysis have become central methods to better understand and analyze online behavior and opinion. However, semantic and sentiment analysis have rarely been combined for joint topic-sentiment modeling which yields semantic topics associated with sentiments. Recent breakthroughs in natural language processing have also not been leveraged for joint topic-sentiment modeling so far. Inspired by these advancements, this paper presents a novel framework for joint topic-sentiment modeling of short texts based on pre-trained language models and a clustering approach. The method leverages techniques from dimensionality reduction and clustering for which multiple algorithms were considered. All configurations were experimentally compared against existing joint topic-sentiment models and an independent sequential baseline. Our framework produced clusters with semantic topic quality scores of up to 0.23 while the best score among the previous approaches was 0.12. The sentiment classification accuracy increased from 0.35 to 0.72 and the uniformity of sentiments within the clusters reached up to 0.9 in contrast to the baseline of 0.56. The presented approach can benefit various research areas such as disaster management where sentiments associated with topics can provide practical useful information.

HEUREKA'24-Optimierung in Verkehr und Transport, Stuttgart, 13rd-14th March 2024

Zur Beschreibung der Attraktivität von Gebieten im Rahmen der Zielwahlmodellierung werden oftmals Informationen über Points-of-Interest (POI) aus OpenStreetMap (OSM) genutzt. Wir haben die Vollständigkeit der OSM-POI-Datenbank für 129 Untersuchungsgebiete mithilfe von Vollerhebungen geprüft. Die Vollständigkeit der OSM-Datenbank unterscheidet sich zwischen einzelnen Kategorien erheblich. OSM ist in den Kategorien Gastronomie und Einzelhandel in weiten Teilen vollständig und nach stichprobenartiger Prüfung im Anwendungsfall für die Modellierung nutzbar. In den Kategorien Dienstleistung mit Kundenverkehr und Medizinische Versorgung fehlen in OSM zumeist eine Vielzahl an POI. Strukturelle Einflüsse räumlicher oder intrinsischer Indikatoren konnten nicht nachgewiesen werden.

IEEE Transactions on Pattern Analysis and Machine Intelligence

The foundation model has recently garnered significant attention due to its potential to revolutionize the field of visual representation learning in a self-supervised manner. While most foundation models are tailored to effectively process RGB images for various visual tasks, there is a noticeable gap in research focused on spectral data, which offers valuable information for scene understanding, especially in remote sensing (RS) applications. To fill this gap, we created for the first time a universal RS foundation model, named SpectralGPT, which is purpose-built to handle spectral RS images using a novel 3D generative pretrained transformer (GPT). Compared to existing foundation models, SpectralGPT 1) accommodates input images with varying sizes, resolutions, time series, and regions in a progressive training fashion, enabling full utilization of extensive RS Big Data; 2) leverages 3D token generation for spatial …

Information

In the early stages of a disaster caused by a natural hazard (e.g., flood), the amount of available and useful information is low. To fill this informational gap, emergency responders are increasingly using data from geo-social media to gain insights from eyewitnesses to build a better understanding of the situation and design effective responses. However, filtering relevant content for this purpose poses a challenge. This work thus presents a comparison of different machine learning models (Naïve Bayes, Random Forest, Support Vector Machine, Convolutional Neural Networks, BERT) for semantic relevance classification of flood-related, German-language Tweets. For this, we relied on a four-category training data set created with the help of experts from human aid organisations. We identified fine-tuned BERT as the most suitable model, averaging a precision of 71% with most of the misclassifications occurring across similar classes. We thus demonstrate that our methodology helps in identifying relevant information for more efficient disaster management.

ERDKUNDE

Heat poses a significant risk to human health, particularly for vulnerable populations, such as pregnant women, older individuals, young children and people with pre-existing medical conditions. In view of this, we formulated a heat stress-avoidant routing approach in Heidelberg, Germany, to ensure mobility and support day-to-day activities in urban areas during heat events. Although the primary focus is on pedestrians, it is also applicable to cyclists. To obtain a nuanced understanding of the needs and demands of the wider population, especially vulnerable groups, and to address the challenge of reducing urban heat stress, we used an inter-and transdisciplinary approach. The needs of vulnerable groups, the public, and the city administration were identified through participatory methods and various tools, including interactive city walks. Solution approaches and adaptation measures to prevent heat stress were evaluated and integrated into the development of a heat-avoiding route service through a co-design process. The findings comprise the identification of perceived hotspots for heat (such as large public spaces in the city centre with low shading levels), the determination of commonly reported symptoms resulting from severe heat (eg, fatigue or lack of concentration), and the assessment of heat adaptation measures that were rated positively, including remaining in the shade and delaying errands. Additionally, we analysed and distinguished between individual and community adaptation strategies. Overall, many respondents did not accurately perceive the risk of heat stress in hot weather, despite severe limitations. As a result, the heat …

Sustainable Cities and Society

As a supplement to the existing public transit system, bike-sharing is considered an effective solution to the “first mile” and “last mile” of travel. While many stakeholders believe that multimodal travel between public transit and bike-sharing can improve urban accessibility and sustainability, few studies have assessed the impact of bike-sharing on existing public transportation systems in terms of efficiency and equality. This research uses three months of mobile phone location data and about 140 million bike-sharing trips (origin–destination, OD) data from Shenzhen, China, to analyze first mile and last mile bike-sharing multimodal travel and measure the impact of bike-sharing on the existing public transportation system in terms of efficiency and equality at different scales. The research finds that bike-sharing is less effective in improving the operational efficiency of urban public transport and creates new inequalities …

ERDKUNDE

Heat poses a significant risk to human health, particularly for vulnerable populations, such as pregnant women, older individuals, young children and people with pre-existing medical conditions. In view of this, we formulated a heat stress-avoidant routing approach in Heidelberg, Germany, to ensure mobility and support day-to-day activities in urban areas during heat events. Although the primary focus is on pedestrians, it is also applicable to cyclists. To obtain a nuanced understanding of the needs and demands of the wider population, especially vulnerable groups, and to address the challenge of reducing urban heat stress, we used an inter-and transdisciplinary approach. The needs of vulnerable groups, the public, and the city administration were identified through participatory methods and various tools, including interactive city walks. Solution approaches and adaptation measures to prevent heat stress were evaluated and integrated into the development of a heat-avoiding route service through a co-design process. The findings comprise the identification of perceived hotspots for heat (such as large public spaces in the city centre with low shading levels), the determination of commonly reported symptoms resulting from severe heat (eg, fatigue or lack of concentration), and the assessment of heat adaptation measures that were rated positively, including remaining in the shade and delaying errands. Additionally, we analysed and distinguished between individual and community adaptation strategies. Overall, many respondents did not accurately perceive the risk of heat stress in hot weather, despite severe limitations. As a result, the heat …

Nature Communications

OpenStreetMap (OSM) has evolved as a popular dataset for global urban analyses, such as assessing progress towards the Sustainable Development Goals. However, many analyses do not account for the uneven spatial coverage of existing data. We employ a machine-learning model to infer the completeness of OSM building stock data for 13,189 urban agglomerations worldwide. For 1,848 urban centres (16% of the urban population), OSM building footprint data exceeds 80% completeness, but completeness remains lower than 20% for 9,163 cities (48% of the urban population). Although OSM data inequalities have recently receded, partially as a result of humanitarian mapping efforts, a complex unequal pattern of spatial biases remains, which vary across various human development index groups, population sizes and geographic regions. Based on these results, we provide recommendations for data …

Proceedings of the OSM Science

Advances in Artificial Intelligence (AI) and, specifically, in Deep Learning (DL) have fostered geospatial analysis and remote sensing, culminating in the establishment of GeoAI [1, 2] and the solidification of research on methodologies and techniques for AI-assisted mapping [3-7]. Nevertheless, a particular challenge lies in the substantial demand for training examples in DL. Manual labelling of these examples is labour-intensive, consuming a considerable amount of time and financial resources. Alternatively, semi or automated labelling of data emerges as a prominent solution, as exemplified by the tool ohsome2label [8], which harnesses data from the OpenStreetMap [9] to label satellite images. However, moving from characterising object types (road, river, building) based on geometry to categorising them by attributes might result in an imbalanced class distribution in the utilised Machine Learning (ML) dataset.Such imbalances are common in numerous practical applications. Learning from skewed datasets can be particularly challenging and often requires non-conventional ML techniques. A comprehensive awareness of the issues associated with class imbalance, as well as strategies for mitigating them, is essential [10]. In the context of spatial data, the distribution of classes can vary from country to country and region to region, adding a new layer of complexity and exacerbating this issue. In this context, an analysis was conducted on the distribution of road types, defined by the values of the OSM" highway" tag, in diverse-profile nations. The aim was to evaluate the extent of class imbalance and to identify any consistent patterns in the …

The recent advance of adapting pre-trained task-agnostic artificial intelligence (AI) models leads to great successes in downstream tasks via fine-tuning, or low-resource (i.e., few-shot and zero-shot) learning. However, when adapting such pre-trained AI models to geographical applications, it is still challenging to find the "sweet spot" of the model's generalizability and specializability (e.g., geographic generalizability v.s. spatial heterogeneity). For instance, a building detection task may require vision models with different parameters across different geographic areas of the world. In this paper, we rethink this interesting topic, namely Geographical Generalizability of GeoAI models, with a case study of detecting OpenStreetMap (OSM) missing buildings across different countries in sub-Saharan Africa. We consider a real-world scenario, in which we first train a Single-Shot Multibox Detection (SSD) base model for OSM …

Environmental Monitoring and Assessment

Spatially explicit information on carbon fluxes related to land use and land cover change (LULCC) is of value for the implementation of local climate change mitigation strategies. However, estimates of these carbon fluxes are often aggregated to larger areas. We estimated committed gross carbon fluxes related to LULCC in Baden-Württemberg, Germany, using different emission factors. In doing so, we compared four different data sources regarding their suitability for estimating the fluxes: (a) a land cover dataset derived from OpenStreetMap (OSMlanduse); (b) OSMlanduse with removal of sliver polygons (OSMlanduse cleaned), (c) OSMlanduse enhanced with a remote sensing time series analysis (OSMlanduse+); (d) the LULCC product of Landschaftsveränderungsdienst (LaVerDi) from the German Federal Agency of Cartography and Geodesy. We produced a high range of carbon flux estimates, mostly caused …

Proceedings of the OSM Science 2023 at State of the Map Europe 2023

OpenStreetMap (OSM) started as a project in 2004 aiming at creating a digital and open map of the world via collaborative mapping, emerging over time to become a community (or a collection of communities)[1] or an ecosystem [2] around the project itself. This ecosystem encompasses local and global communities of data and software developers creating a large number of tools and services, eg for spatial data infrastructures [3], disaster response [4], and routing [5]. Additionally, a new scientific field focusing on OSM is emerging with academic researchers investigating the different scientific aspects of the living OSM community [6–8]. The Academic Track at the annual State of the Map (SotM) conference, with five editions from 2018 to 2022 has become a knowledge hub for gathering and sharing recent progress in OSM-related research and scientific findings directly with the broad OSM community. Moreover, the 2019 and 2020 editions of this Track have led to the first special issue of scientific articles dedicated to OSM [9], which first formalized and used the term “OSM Science” outside informal conversations in SotM and the OSM-science mailing list [10](with one exception being Haklay’s reference to ‘OSM studies’[11]). In its sixth edition, the Academic Track starts to use the new name of “OSM Science” referring to

ISPRS International Journal of Geo-Information

Natural hazards threaten millions of people all over the world. To address this risk, exposure and vulnerability models with high resolution data are essential. However, in many areas of the world, exposure models are rather coarse and are aggregated over large areas. Although OpenStreetMap (OSM) offers great potential to assess risk at a detailed building-by-building level, the completeness of OSM building footprints is still heterogeneous. We present an approach to close this gap by means of crowd-sourcing based on the mobile app MapSwipe, where volunteers swipe through satellite images of a region collecting user feedback on classification tasks. For our application, MapSwipe was extended by a completeness feature that allows to classify a tile as “no building”, “complete” or “incomplete”. To assess the quality of the produced data, the completeness feature was applied to four regions. The MapSwipe-based assessment was compared with an intrinsic approach to quantify completeness and with the prediction of an existing model. Our results show that the crowd-sourced approach yields a reasonable classification performance of the completeness of OSM building footprints. Results showed that the MapSwipe-based assessment produced consistent estimates for the case study regions while the other two approaches showed a higher variability. Our study also revealed that volunteers tend to classify nearly completely mapped tiles as “complete”, especially in areas with a high OSM building density. Another factor that influenced the classification performance was the level of alignment of the OSM layer with the satellite imagery.

Engineering Proceedings

Urban heat islands, characterized by higher temperatures in cities compared to surrounding areas, have been studied using various techniques. However, during heat waves, existing models often underestimate the intensity of these heat islands compared to empirical measurements. To address this, an hourly time-series-based model for predicting heat island intensity during heat wave conditions is proposed. The model was developed and validated using empirical data from the National Monitoring Network in Temuco, Chile. Results indicate a strong correlation (r > 0.98) between the model’s predictions and actual monitoring data. Additionally, the study emphasizes the importance of considering the unique microclimatic characteristics and built environment of each city when modelling urban heat islands. Factors such as urban morphology, land cover, and anthropogenic heat emissions interact in complex ways, necessitating tailored modelling approaches for the accurate representation of heat island phenomena.

Available at SSRN 4643541

Promoting urban well-being is a significant societal issue in the context of rapid urbanization. Past research has highlighted that interaction with urban green spaces, such as parks and forests, is key in promoting urban well-being. However, there is limited knowledge regarding the potential in promoting well-being from non-nature elements. In the present study, we explored whether interacting with art could enhance well-being in urban street contexts. In our field experiment, we built two interventions on urban streets, decorating them with either laminated art prints or green elements. We measured subjective and physiological well-being before and after the interaction with the interventions. With this paradigm, we assessed if, not only green, but also artistic interventions can improve well-being. Our results showed that, after interacting with the artistic intervention in an urban environment, the participants reported reduced feelings of anxiety, stress, and negative mood as they did with the green intervention. Further, our results indicate that improvements in well-being were linked to participants’ evaluations of the testing location (restorativeness), of aesthetic quality of the intervention (eg, beauty, meaningfulness), and of their overall experience (eg, enjoyment). These findings have significant implications in promoting urban well-being and city planning, as they highlight the potential of art as a novel tool for enhancing urban well-being.

International Journal of Applied Earth Observation and Geoinformation

Green Plastic Cover (GPC) has been widely used in construction sites of China as the main measure for dust suppression. As a unique land cover in China, GPC could be viewed as a sign for evaluating the intensity of urban construction. Therefore, time series GPC maps could provide a new perspective to understand the pattern of urban development, including both urban expansion and urban shrinkage. The objective of this study is to present a novel framework for detection of urban development patterns based on high resolution GPC maps generated from Google Earth Engine (GEE) cloud platform. Specifically, we first generated the GPC maps of 137 districts and counties in Shandong Province of China from 2018 to 2022 by combining time series spectral features and textural features derived from Sentinel-1 and Sentinel-2 images provided by GEE cloud platform. Afterwards, we designed a GPC-based urban …

International Journal of Applied Earth Observation and Geoinformation

Corn is the dominant crop planted in Northeast China, and its accurate and timely mapping is important for food security and agricultural management in China. However, the absence of enough labels is challenging for corn accurate mapping in a regional area using machine learning methods or deep learning methods. In this study, an efficient way of automatic labelling and mapping of corn planted areas by combining Global Ecosystem Dynamics Investigation (GEDI) data and Sentinel-2 images is proposed. We explore the height and vertical structure differences between corn and other crops derived from GEDI features and generate labels automatically by referencing crop type products and transferring models from historical years. The trained learning networks of automatic labelling from GEDI points and the trained decision trees of the Random Forest (RF) classifier can be transferred to corn mapping in …

International Journal of Applied Earth Observation and Geoinformation

The carbon sinks of North American boreal forests have been threatened by global warming and forest disturbances in recent decades, but knowledge about the carbon balance of these forests in recent years remains unknown. We tracked annual aboveground carbon (AGC) changes from 2016 to 2021 across the forest regions of NASA’s Arctic Boreal Vulnerability Experiment (ABoVE) core study domain, using Vegetation Optical Depth derived from low-frequency passive microwave observations. The results showed that these forests showed a net AGC increase of + 28.49 Tg C/yr during the study period, with total AGC gains of + 219.34 Tg C/yr counteracting total AGC losses of −190.86 Tg C/yr. Forest degradation (-162.21 Tg C/yr), defined as a reduction in the capacity of forest to provide goods and services, contributes 5 times more to the total AGC loss than forest cover loss (-28.65 Tg C/yr), defined as the …

International Journal of Applied Earth Observation and Geoinformation

Primary forests in Indonesia are in high decline. The increase in population exacerbates forest reductions, as forests are changed to settlements. This impacts the loss of biodiversity and animals in Indonesia. An important way to prevent the loss of biodiversity and animals is to conserve crucial areas. Spatial modeling can be done to detect conservation areas that are important for the future. This study analyzes the index of forest ecosystem services and habitat suitability of extinct animals to determine priority conservation areas. Here we predict forest areas that are indicated to be lost in the future. We use integrated spatial data using GIS (Geography Information System) to determine priority conservation areas. From the results, we predict that there will be a change in land cover to settlement by 2030. This causes the ecosystem service index (ESI) value to decrease from an initially high value each year. In terms of …

International Journal of Applied Earth Observation and Geoinformation

Content produced within the scope of the Agenda “NEXUS–Pacto de Inovação–Transição Verde e Digital para Transportes, Logística e Mobilidade”, financed by the Portuguese Recovery and Resilience Plan (PRR), with no. C645112083-00000059 (investment project no. 53). The research was also funded by the INOVC+ program (The InovC+ Intelligent Innovation Ecosystem of the Central Region project is co-funded by Centro 2020, Portugal 2020, through FEDER, through project BATDRON (“Aquisição de dados batimétricos por drone durante eventos de agitação marítima intensa”). Thanks are due FCT/MCTES for the financial support to CESAM,(UIDP/50017/2020+ UIDB/50017/2020+ LA/P/0094/2020), through national funds.

International Journal of Applied Earth Observation and Geoinformation

Forest Change Detection (FCD) is a critical component of natural resource monitoring and conservation strategies, enabling informed decision-making. Various methods utilizing the power of artificial intelligence (AI) have been developed for detecting and categorizing changes in forest cover using remote sensing (RS) data. One prominent AI-powered approach is the U-Net, a deep learning (DL) architecture famous for its segmentation proficiency. However, the standard U-Net architecture fails to effectively capture intricate spatial dependencies and long-range contextual information present in remote sensing imagery. To address this research gap, we introduce an attention-residual-based novel DL model which leverages the U-Net architecture and Sentinel-2 satellite images to map alterations in forest vegetation cover in the tropical region. Our novel model enhances the U-Net architecture by seamlessly integrating the strengths of the U-Net, harnessing attention mechanisms strategically to amplify crucial features, and leveraging cutting-edge residual connections to facilitate the smooth flow of information and gradient propagation. These meticulous design choices enabled the precise feature extraction, resulting in improved computational performance of the proposed method compared to the Standard U-Net, Deeplabv3+, Deep Res-U-Net, and Attention U-Net. The classification results demonstrate the enhanced efficiency of our model, achieving a Mean Intersection over Union (MIoU) of 0.9330 on our test dataset. This performance surpasses the Attention U-Net (0.9146), Standard U-Net (0.9029), Deeplabv3+(0.9247), and Deep Res-U-Net …

International Journal of Applied Earth Observation and Geoinformation

Burn severity has been widely studied. Typical approaches use spectral differencing indices from remotely sensed data to extrapolate in-situ severity assessments. Next generation geostationary data offer near-continuous fire behaviour information, which has been used for fire detection and monitoring but remains underutilized for fire impact estimation. Here, we explore the association between remotely sensed fire intensity metrics and spectral differencing severity indices to understand whether and where they describe similar wildfire effects. The commonly used Differenced Normalised Burn Ratio (dNBR) severity index was calculated for Advanced Himawari Imager (AHI − 2 km) and Sentinel-2 (20 m) data and compared to different Fire Radiative Power (FRP) metrics derived from fire hotspot detections from AHI data across Australia. The comparison was implemented through different stratifications based on …

International Journal of Applied Earth Observation and Geoinformation

Hyperspectral Image Classification (HSIC) is a challenging task due to the high-dimensional nature of Hyperspectral Imaging (HSI) data and the complex relationships between spectral and spatial information. This paper proposes a Graph-Infused Hybrid spatial–spectral Transformer (GFormer) for HSIC. The GFormer combines the power of graph and spatial–spectral transformer to capture both spectral relationships and spatial context. We represent the HSI data as a graph, where nodes represent pixels and edges capture spectral similarities. By incorporating an attention mechanism, the GFormer learns spatial–spectral fusion representations, allowing it to effectively discriminate between different classes. The model can capture long-range dependencies among spectral bands, enabling it to understand complex interactions in the HSI data. Moreover, the GFormer adapts to different spectral resolutions by …

International Journal of Applied Earth Observation and Geoinformation

The accurate estimation of biomass burning emissions has played a crucial role in air quality and climate forecast modeling. Satellite-based fire radiative power (FRP) has proven effective for calculating biomass burning emissions. However, FRP-based emission estimations in East Asia often rely on polar-orbiting satellites owing to the unstable performance of Japan Aerospace Exploration Agency Advanced Himawari Imager (JAXA AHI) from poor detection capability and unproper FRP retrieval method. To address this, we improve the FRP by machine learning based on mid-infrared (MIR) radiance method, leveraging the superior fire detection model developed in our previous study. In addition, we propose a multi-satellite distance-based weighted ensemble FRP estimation method. Compared to traditional MIR radiance methods, the machine learning-based FRP estimation model exhibited promising …

International Journal of Applied Earth Observation and Geoinformation

Topography determines run-off direction, redistributes groundwater, and affects land surface solar radiation loads and the associated evaporative forcing, consequently, topography can modulate the impact of drought and heat waves on ecosystems. This topographic modulation effect, which typically occurs at the local scale, is often overlooked when assessing ecosystem drought responses using moderate-to-coarse spatial resolution satellite observations, such as the Moderate-resolution Imaging Spectroradiometer (MODIS) imagery. Sentinel-2 and Landsat imagery with finer resolution are suitable for monitoring changes at the local scale, however, studies relying on single vegetation metrics may fail to get a holistic picture of vegetation drought responses, particularly for forests that have complex physiological mechanisms. Here, we performed a comprehensive assessment of the topographic effects on …

International journal of applied earth observation and geoinformation

A semi-analytical model is developed for estimating the spectral diffuse attenuation coefficient of downwelling irradiance (Kd(λ)) in inland and coastal waters. The model works as a function of the inherent optical properties (absorption and backscattering), depth, and solar zenith angle. Results of this model are validated using a large number of in-situ measurements of Kd(λ) in clear oceanic, turbid coastal and productive lagoon waters. To further evaluate its relative performance, Kd(λ) values obtained from this model are compared with results from three existing models. Validation results show that the present model is a better descriptor of Kd(λ) and shows an overall better performance compared to the existing models. The applicability of the present model is further tested on two Hyperspectral Imager for the Coastal Ocean (HICO) remote sensing images acquired simultaneously with our field measurements. The …

International Journal of Applied Earth Observation and Geoinformation

Detailed maps on the spatial and temporal distribution of crops are key for a better understanding of agricultural practices and for food security management. Multi-temporal remote sensing data and deep learning (DL) have been extensively studied for deriving accurate crop maps. However, strategies to solve the problem of transferring crop classification models over time, e.g., training the model with data for a recent year and mapping back to the past, have not been fully explored. This is due to the lack of a generalized method for aggregating optical data with regard to the irregularity in annual clear sky observations and the scarcity of multi-annual crop reference data to support a more generalized DL model. In this study, we tackled these challenges by introducing a method namely Temporal Encoding (TE) to capture the irregular phenological information. Subsequently, we adapted and integrated two methods, i …

International Journal of Applied Earth Observation and Geoinformation

Accurate and up-to-date mapping of the human population is fundamental for a wide range of disciplines, from effective governance and establishing policies to disaster management and crisis dilution. The traditional method of gathering population data through census is costly and time-consuming. Recently, with the availability of large amounts of Earth observation data sets, deep learning methods have been explored for population estimation; however, they are either limited by census data availability, inter-regional evaluations, or transparency. In this paper, we present an end-to-end interpretable deep learning framework for large-scale population estimation at a resolution of 1 km that uses only the publicly available data sets and does not rely on census data for inference. The architecture is based on a modification of the common ResNet-50 architecture tailored to analyze both image-like and vector-like data …

International Journal of Applied Earth Observation and Geoinformation

Meteorological drought precedes the agricultural drought and studying the propagation time from meteorological to agricultural drought can substantially reduce agricultural losses. To find this propagation time between the meteorological and agricultural drought, this study analyzed the copula-based conditional probability between the Standardized Precipitation Index at 12 timescales (SPI-1 to12, meteorological drought) and Standardized Soil Moisture Index at 1 month timescale (SSI-1, agricultural drought), over the fifteen Agro-Climatic Zones (ACZs) of India. SSI is computed using a total column Soil Moisture (SM) derived from ESACCI SM using the Statistical Soil Moisture Profile (SSMP) model. The SSMP-based ESACCI SM is positively correlated (Correlation Coefficient of 0.871) with ERA5 Land SM. To compute the conditional probability, three copulas namely Frank, Clayton, and Gumbel copulas are fitted …

International Journal of Applied Earth Observation and Geoinformation

Spatial scene similarity plays a crucial role in spatial cognition, as it enables us to understand and compare different spatial scenes and their relationships. However, understanding spatial scenes is a complex task. While existing literature has contributed to spatial scene representation learning, these methods primarily focus on comprehending the spatial relationships among objects, often neglecting their semantic features. Furthermore, there is a lack of scene representation learning methods that can seamlessly handle different types of spatial objects (e.g., points, polylines, and polygons) in a scene. Moreover, since expert knowledge is required for the annotation process of spatial scene understanding, publicly available high-quality annotation data has a limited size which usually leads to suboptimal results. To address these issues, we propose a novel multi-scale spatial scene encoding model called …

International Journal of Applied Earth Observation and Geoinformation

Urban trees provide important ecosystem services to improve cities’ liveability and sustainability. Leaf chlorophyll content (C ab) estimation by remote sensing can help monitor tree health efficiently. However, the C ab retrieval of urban trees is challenging because of the complex canopy structures, backgrounds, and illuminations conditions. This paper proposed an automatic method for partitioning sunlit/shaded pixels and removal of bright-specular/dark-hole and background pixels. In addition, we proposed a new index, the Urban Tree Chlorophyll Index (UTCI), defined as UTCI=(ρ 709-ρ 697)/(ρ 709-ρ 686), based on the simulated hyperspectral images of urban tree using radiative transfer model. This proposed UTCI index outperforms existing narrow-band indices (NBIs) for estimating C ab for complex canopy structures, backgrounds, and illumination conditions evaluated using simulated hyperspectral images …

International Journal of Applied Earth Observation and Geoinformation

The inversion of inherent optical properties (IOPs) and chlorophyll a (Chla) is one of the key objectives in water color remote sensing, and hyperspectral remote sensing with rich spectral information makes precise inversion possible. In this study, we developed a semi-analytical estimation method for inland water IOPs based on the quasi-analytical algorithm (QAA). Considering the complex optical characteristics of inland waters, empirical parameter regional optimization was conducted. Furthermore, a dual-band joint inversion strategy and Gaussian function fitting method were utilized to optimize the solution processes for the backscattering coefficient of particles (bbp) and the absorption coefficient of phytoplankton pigments (aph), respectively. This approach overcomes the limitations of single-band bbp inversion in inland waters. In addition, it directly decomposes the absorption coefficient to obtain aph using a …

International Journal of Applied Earth Observation and Geoinformation

Satellite-derived bathymetry plays a significant role in characterizing river systems, furnishing invaluable insights for applications such as flood risk management. In this paper, we introduce a bathymetry inversion framework, namely reflectance transformation - convolutional neural network (RT-CNN), geared towards long river segments, exemplified by a 210-kilometer stretch of the Bei River's in South China. The framework hinges on a neural network driven by a reflectance transformation model, an optical construct that harnesses radiance data from visible, near-infrared, and shortwave infrared bands. This modified input undergoes spatial–temporal fusion and convolutional neural network processing, culminating in high-resolution (10-meter) bathymetric estimations. The RT-CNN approach adeptly blends Landsat and Sentinel imagery with a substantial dataset of over 18,000 SONAR measurements, integrating …

International Journal of Applied Earth Observation and Geoinformation

The 2014 Northwest Territories fires are one of the largest wildfires in history. However, it is difficult to explain what caused such devastating wildfires simply with meteorological conditions and hydrological drought. There is a lack of large-scale Near-Real-Time (NRT) observations that characterize fuel conditions. To fill this research gap, we provide the new earth observations that the meso-scale vegetation heat represented by L-band microwave-retrieved fuel (or canopy) temperature serves as a predictor of fire spread and lightning. We studied two million-ha-scale extreme fire events in the Northwest Territories in 2014 and British Columbia in 2018 to demonstrate that preheated endothermic vegetation condition (canopy temperature>295 K) ahead of flaming is a prerequisite for mega-fires. Canopy temperature is thus proposed as an indicator to modulate convective heating ahead of combustion, and fire spread …

International Journal of Applied Earth Observation and Geoinformation

The success of transformer networks in the natural language processing and 2D vision domains has encouraged the adaptation of transformers to 3D computer vision tasks. However, most of the existing approaches employ standard backpropagation (SBP). SBP requires the storage of model activations on a forward pass for use during the backward pass, making their memory complexity linearly proportional to model depth, hence, inefficient. Furthermore, most 3D point transformers use the classic QKV matrix multiplication design which comes with a memory bottleneck. To address these issues, we propose a memory-efficient point transformer that makes use of reversible functions and linearized self-attention to minimize SBP and transformer memory complexities, respectively. Additionally, rather than the usual UNet architectural design for segmentation, we adopt a ∇-shaped design to capture multi-size …