Monitoring of toxic cyanobacterial blooms in Lalla Takerkoust reservoir by satellite imagery and microcystin transfer to surrounding farms.

Cyanobacterial harmful algal blooms (CyanoHABs) threaten public health and freshwater ecosystems worldwide. In this study, our main goal was to explore the dynamics of cyanobacterial blooms and how microcystins (MCs) move from the Lalla Takerkoust reservoir to the nearby farms. We used Landsat imagery, molecular analysis, collecting and analyzing physicochemical data, and assessing toxins using HPLC. Our investigation identified two cyanobacterial species responsible for the blooms: Microcystis sp. and Synechococcus sp. Our Microcystis strain produced three MC variants (MC-RR, MC-YR, and MC-LR), with MC-RR exhibiting the highest concentrations in dissolved and intracellular toxins. In contrast, our Synechococcus strain did not produce any detectable toxins. To validate our Normalized Difference Vegetation Index (NDVI) results, we utilized limnological data, including algal cell counts, and quantified MCs in freeze-dried Microcystis bloom samples collected from the reservoir. Our study revealed patterns and trends in cyanobacterial proliferation in the reservoir over 30 years and presented a historical map of the area of cyanobacterial infestation using the NDVI method. The study found that MC-LR accumulates near the water surface due to the buoyancy of Microcystis. The maximum concentration of MC-LR in the reservoir water was 160 µg L-1. In contrast, 4 km downstream of the reservoir, the concentration decreased by a factor of 5.39 to 29.63 µgL-1, indicating a decrease in MC-LR concentration with increasing distance from the bloom source. Similarly, the MC-YR concentration decreased by a factor of 2.98 for the same distance. Interestingly, the MC distribution varied with depth, with MC-LR dominating at the water surface and MC-YR at the reservoir outlet at a water depth of 10 m. Our findings highlight the impact of nutrient concentrations, environmental factors, and transfer processes on bloom dynamics and MC distribution. We emphasize the need for effective management strategies to minimize toxin transfer and ensure public health and safety.

An evaluative technique for drought impact on variation in agricultural LULC using remote sensing and machine learning.

Drought events threaten freshwater reservoirs and agricultural productivity, particularly in semi-arid regions characterized by erratic rainfall. This study evaluates a novel technique for assessing the impact of drought on LULC variations in the context of climate change from 2018 to 2022. Various data sources were harnessed, encompassing Sentinel-2 satellite imagery for LULC classification, climate data from the CHIRPS and AgERA5 databases, geomorphological data from JAXA's ALOS satellite, and a drought indicator (Vegetation Health Index (VHI)) derived from MODIS data. Two classifier models, namely gradient tree boost (GTB) and random forest (RF), were trained and assessed for LULC classification, with performance evaluated by overall accuracy (OA) and kappa coefficient (K). Notably, the GTB model exhibited superior performance, with OA > 90% and a K > 0.9. Over the period from 2018 to 2022, Fez experienced LULC changes of 19.92% expansion in built-up areas, a 34.86% increase in bare land, a 17.86% reduction in water bodies, and a 37.30% decrease in agricultural land. Positive correlations of 0.81 and 0.89 were observed between changes in agricultural LULC, rainfall, and VHI. Furthermore, mild drought conditions were identified in the years 2020 and 2022. This study emphasizes the importance of AI and remote sensing techniques in assessing drought and environmental changes, with potential applications for improving existing drought monitoring systems.

Unveiling the landscape predictors of resilient vegetation in coastal wetlands to inform conservation in the face of climate extremes.

Unveiling spatial variation in vegetation resilience to climate extremes can inform effective conservation planning under climate change. Although many conservation efforts are implemented on landscape scales, they often remain blind to landscape variation in vegetation resilience. We explored the distribution of drought-resilient vegetation (i.e., vegetation that could withstand and quickly recover from drought) and its predictors across a heterogeneous coastal landscape under long-term wetland conversion, through a series of high-resolution satellite image interpretations, spatial analyses, and nonlinear modelling. We found that vegetation varied greatly in drought resilience across the coastal wetland landscape and that drought-resilient vegetation could be predicted with distances to coastline and tidal channel. Specifically, drought-resilient vegetation exhibited a nearly bimodal distribution and had a seaward optimum at ~2 km from coastline (corresponding to an inundation frequency of ~30%), a pattern particularly pronounced in areas further away from tidal channels. Furthermore, we found that areas with drought-resilient vegetation were more likely to be eliminated by wetland conversion. Even in protected areas where wetland conversion was slowed, drought-resilient vegetation was increasingly lost to wetland conversion at its landward optimum in combination with rapid plant invasions at its seaward optimum. Our study highlights that the distribution of drought-resilient vegetation can be predicted using landscape features but without incorporating this predictive understanding, conservation efforts may risk failing in the face of climate extremes.

Generation and classification of patch-based land use and land cover dataset in diverse Indian landscapes: a comparative study of machine learning and deep learning models.

In the context of environmental and social applications, the analysis of land use and land cover (LULC) holds immense significance. The growing accessibility of remote sensing (RS) data has led to the development of LULC benchmark datasets, especially pivotal for intricate image classification tasks. This study addresses the scarcity of such benchmark datasets across diverse settings, with a particular focus on the distinctive landscape of India. The study entails the creation of patch-based datasets, consisting of 4000 labelled images spanning four distinct LULC classes derived from Sentinel-2 satellite imagery. For the subsequent classification task, three traditional machine learning (ML) models and three convolutional neural networks (CNNs) were employed. Despite facing several challenges throughout the process of dataset generation and subsequent classification, the CNN models consistently attained an overall accuracy of 90% or more. Notably, one of the ML models stood out with 96% accuracy, surpassing CNNs in this specific context. The study also conducts a comparative analysis of ML models on existing benchmark datasets, revealing higher prediction accuracy when dealing with fewer LULC classes. Thus, the selection of an appropriate model hinges on the given task, available resources, and the necessary trade-offs between performance and efficiency, particularly crucial in resource-constrained settings. The standardized benchmark dataset contributes valuable insights into the relative performance of deep CNN and ML models in LULC classification, providing a comprehensive understanding of their strengths and weaknesses.

Assessment of the environmental impacts of conflict-driven Internally Displaced Persons: A sentinel-2 satellite based analysis of land use/cover changes in the Kas locality, Darfur, Sudan.

Internal displacement of populations due to armed conflicts can substantially impact a region's Land Use and Land Cover (LULC) and the efforts towards the achievement of Sustainable Development Goals (SDGs). The objective of this study was to determine the effects of conflict-driven Internally Displaced Persons (IDPs) on vegetation cover and environmental sustainability in the Kas locality of Darfur, Sudan. Supervised classification and change analysis were performed on Sentinel-2 satellite images for the years 2016 and 2022 using QGIS software. The Sentinel-2 Level 2A data were analysed using the Random Forest (RF) Machine Learning (ML) classifier. Five land cover types were successfully classified (agricultural land, vegetation cover, built-up area, sand, and bareland) with overall accuracies of more than 86% and Kappa coefficients greater than 0.74. The results revealed a 35.33% (-10.20 km2) decline in vegetation cover area over the six-year study period, equivalent to an average annual loss rate of -5.89% (-1.70 km2) of vegetation cover. In contrast, agricultural land and built-up areas increased by 17.53% (98.12 km2) and 60.53% (5.29 km2) respectively between the two study years. The trends of the changes among different LULC classes suggest potential influences of human activities especially the IDPs, natural processes, and a combination of both in the study area. This study highlights the impacts of IDPs on natural resources and land cover patterns in a conflict-affected region. It also offers pertinent data that can support decision-makers in restoring the affected areas and preventing further environmental degradation for sustainability.

Satellite mapping reveals phytoplankton biomass's spatio-temporal dynamics and responses to environmental factors in a eutrophic inland lake.

Chlorophyll a (Chla) concentration can be used as an indicator of algal biomass, and the accumulation of algal biomass in water column is essential for the emergence of surface blooms. By using Moderate Resolution Imaging Spectrometer (MODIS) data, a machine learning algorithm was previously developed to assess algal biomass within the euphotic depth (Beu). Here, a long-term Beu dataset of Lake Taihu from 2003 to 2020 was generated to examine its spatio-temporal dynamics, sensitivity to environmental factors, and variations in comparison to the surface algal bloom area. During this period, the daily Beu (total Beu within the whole lake) exhibited temporal fluctuations between 40 and 90 t Chla, with an annual average of 63.32 ± 5.23 t Chla. Notably, it reached its highest levels in 2007 (72.34 t Chla) and 2017 (73.57 t Chla). Moreover, it demonstrated a clear increasing trend of 0.197 t Chla/y from 2003 to 2007, followed by a slight decrease of 0.247 t Chla/y after 2017. Seasonal variation showed a bimodal annual cycle, characterized by a minor peak in March âˆ¼ April and a major peak in July âˆ¼ September. Spatially, the average pixel-based Beu (total Beu of a unit water column) ranged from 21.17 to 49.85 mg Chla, with high values predominantly distributed in the northwest region and low values in the central region. The sensitivity of Beu to environmental factors varies depending on regions and time scales. Temperature has a significant impact on monthly variation (65.73%), while the level of nutrient concentrations influences annual variation (55.06%). Wind speed, temperature, and hydrodynamic conditions collectively influence the spatial distribution of Beu throughout the entire lake. Algal bloom biomass can capture trend changes in two mutant years as well as bimodal phenological changes compared to surface algal bloom area. This study can provide a basis for scientific evaluation of water environment and a reference for monitoring algal biomass in other similar eutrophic lakes.

Land use and land cover dynamics in the Upper Ganga Riverine Wetland: unraveling ecosystem services over two decades.

Anthropogenic activities have drastically transformed natural landscapes, profoundly impacting land use and land cover (LULC) and, consequently, the provision and functionality of ecosystem service values (ESVs). Evaluating the changes in LULC and their influence on ESVs is imperative to protect ecologically fragile ecosystems from degradation. This study focuses on a highly sensitive Upper Ganga riverine wetland in India, covering Hapur, Amroha, Bulandshahr, and Sambhal districts, which is well-known for its significant endemic flora and fauna. The study analyzes the subtle variability in ecosystem services offered by the various LULC biomes, including riverine wetland, built-up, cropland, forest, sandbar, and unused land. LULC classification is carried out using Landsat satellite imagery 5 and 8 for the years 2000, 2010, and 2020, using the random forest method. The spatiotemporal changing pattern of ESVs is assessed utilizing the value transfer method with two distinct value coefficients: global value coefficients (C14) for a worldwide perspective and modified local value coefficients X08 for a more specific local context. The results show a significant increase in built-up and unused land, with a corresponding decrease in wetlands and forests from 2000 to 2020. The combined ESVs for all the districts are worth US $5072 million (C14) and US $2139 million (X08) in the year 2000, which declined to US $4510 million (C14) and US $1770 million (X08) in the year 2020. The sensitivity analysis reveals that the coefficient of sensitivity (CS) is below one for all biomes, suggesting the robustness of the employed value coefficients in estimating ESVs. Moreover, the analysis identifies cropland, followed by forests and wetlands, as the LULC biomes most responsive to changes. This research provides crucial insights to stakeholders and policymakers for developing sustainable land management practices aimed at enhancing the ecological worth of the Upper Ganga Riverine Wetland.

Assessing Tunisia's urban air quality using combined lichens and Sentinel-5 satellite integration.

In Tunisia, urban air pollution is becoming a bigger problem. This study used a combined strategy of biomonitoring with lichens and satellite mapping with Sentinel-5 satellite data processed in Google Earth Engine (GEE) to assess the air quality over metropolitan Tunis. Lichen diversity was surveyed across the green spaces of the Faculty of Science of Tunisia sites, revealing 15 species with a predominance of pollution-tolerant genera. The Index of Atmospheric Purity (IAP) calculated from the lichen data indicated poor air quality. Spatial patterns of pollutants sulfur dioxide (SO2), ozone (O3), nitrogen dioxide (NO2), carbon monoxide (CO), and aerosol index across Greater Tunis were analyzed from Sentinel-5 datasets on the GEE platform. The higher values of these indices in the research area indicate that it may be impacted by industrial activity and highlight the considerable role that vehicle traffic plays in air pollution. The results of the IAP, IBL, and the combined ground-based biomonitoring and satellite mapping techniques confirm poor air quality and an environment affected by atmospheric pollutants which will enable proactive air quality management strategies to be put in place in Tunisia's rapidly expanding cities.

Exploring the spatial association between the distribution of temperature and urban morphology with green view index.

Urban heat islands will occur if city neighborhoods contain insufficient green spaces to create a comfortable environment, and residents' health will be adversely affected. Current satellite imagery can only effectively identify large-scale green spaces and cannot capture street trees or potted plants within three-dimensional building spaces. In this study, we used a deep convolutional neural network semantic segmentation model on Google Street View to extract environmental features at the neighborhood level in Taipei City, Taiwan, including the green vegetation index (GVI), building view factor, and sky view factor. Monthly temperature data from 2018 to 2021 with a 0.01° spatial resolution were used. We applied a linear mixed-effects model and geographically weighted regression to explore the association between pedestrian-level green spaces and ambient temperature, controlling for seasons, land use information, and traffic volume. Their results indicated that a higher GVI was significantly associated with lower ambient temperatures and temperature differences. Locations with higher traffic flows or specific land uses, such as religious or governmental, are associated with higher ambient temperatures. In conclusion, the GVI from street-view imagery at the community level can improve the understanding of urban green spaces and evaluate their effects in association with other social and environmental indicators.

Multispectral analysis-ready satellite data for three East African mountain ecosystems.

The East African mountain ecosystems are facing increasing threats due to global change, putting their unique socio-ecological systems at risk. To monitor and understand these changes, researchers and stakeholders require accessible analysis-ready remote sensing data. Although satellite data is available for many applications, it often lacks accurate geometric orientation and has extensive cloud cover. This can generate misleading results and make it unreliable for time-series analysis. Therefore, it needs comprehensive processing before usage, which encompasses multi-step operations, requiring large computational and storage capacities, as well as expert knowledge. Here, we provide high-quality, atmospherically corrected, and cloud-free analysis-ready Sentinel-2 imagery for the Bale Mountains (Ethiopia), Mounts Kilimanjaro and Meru (Tanzania) ecosystems in East Africa. Our dataset ranges from 2017 to 2021 and is provided as monthly and annual aggregated products together with 24 spectral indices. Our dataset enables researchers and stakeholders to conduct immediate and impactful analyses. These applications can include vegetation mapping, wildlife habitat assessment, land cover change detection, ecosystem monitoring, and climate change research.

Challenges for monitoring artificial turf expansion with satellite remote sensing.

Urban green spaces are central components of urban ecosystems, providing refuge for wildlife while helping 'future proof' cities against climate change. Conversion of urban green spaces to artificial turf has become increasingly popular in various developed countries, such as the UK, leading to reduced urban ecosystem services delivery. To date, there is no established satellite remote sensing method for reliably detecting and mapping artificial turf expansion at scale. We here assess the combined use of very high-resolution multispectral satellite imagery and classical, open source, supervised classification approaches to map artificial lawns in a typical British city. Both object-based and pixel-based classifications struggled to reliably detect artificial turf, with large patches of artificial turf not being any more reliably identified than small patches of artificial turf. As urban ecosystems are increasingly recognised for their key contributions to human wellbeing and health, the poor performance of these standard methods highlights the urgency of developing and applying new, easily accessible approaches for the monitoring of these important ecosystems.

Comparison of the monitoring of surface deformations in open-pit mines with Sentinel-1A and TerraSAR-X satellite radar data.

In case necessary precautions are not taken in surface mines, serious accidents and loss of life may occur, particularly due to large mass displacements. It is extremely important to identify the early warning signs of these displacements and take the necessary precautions. In this study, free medium-resolution satellite radar images from the European Space Agency's (ESA) C-band Sentinel-1A satellite and commercial high-resolution satellite radar images (SAR, Synthetic Aperture Radar) from the Deutsches Zentrum für Luft- und Raumfahrt's (DLR) X-band TerraSAR-X satellite were obtained, and it was attempted to reveal the traceability and adequacy of monitoring of deformations and possible mass displacements in the dump site of an open-pit coal mine. The compatibility of the results obtained from the satellite radar data with two devices of Global Positioning System (GPS) which were installed in the field was evaluated. Furthermore, the velocity results in the Line Of Sight (LOS) direction and vertical deformation velocity results obtained with all three approaches (GPS/Sentinel-1A, GPS/TerraSAR-X, and Sentinel-1A/TerraSAR-X) were compared. It was observed that the results were statistically equal and the directions of movement were similar/compatible. The result of this study showed that deformations at mine sites can be monitored with sufficient accuracy for early warning with free Sentinel-1A satellite data, although the TerraSAR-X satellite offers a higher resolution.

A labelled dataset to classify direct deforestation drivers from Earth Observation imagery in Cameroon.

Understanding direct deforestation drivers at a fine spatial and temporal scale is needed to design appropriate measures for forest management and monitoring. To achieve this, reference datasets with which to design Artificial Intelligence (AI) approaches to classify direct deforestation drivers within areas experiencing forest loss in a detailed, comprehensive and locally-adapted way are needed. This is the case for Cameroon, in the Congo Basin, which has known increasing deforestation rates in recent years. Here, we created an Earth Observation dataset with associated labels to classify detailed direct deforestation drivers in Cameroon, which includes satellite imagery (Landsat and PlanetScope) and auxiliary data on infrastructure and biophysical properties. The dataset provides the following fifteen labels: oil palm, timber, fruit, rubber and other-large scale plantations; grassland/shrubland; small-scale oil palm or maize plantations and other small-scale agriculture; mining; selective logging; infrastructure; wildfires; hunting; and other.

The rectangular tile classification model based on Sentinel integrated images enhances grassland mapping accuracy: A case study in Ordos, China.

Arid zone grassland is a crucial component of terrestrial ecosystems and plays a significant role in ecosystem protection and soil erosion prevention. However, accurately mapping grassland spatial information in arid zones presents a great challenge. The accuracy of remote sensing grassland mapping in arid zones is affected by spectral variability caused by the highly diverse landscapes. In this study, we explored the potential of a rectangular tile classification model, constructed using the random forest algorithm and integrated images from Sentinel-1A (synthetic aperture radar imagery) and Sentinel-2 (optical imagery), to enhance the accuracy of grassland mapping in the semiarid to arid regions of Ordos, China. Monthly Sentinel-1A median value images were synthesised, and four MODIS vegetation index mean value curves (NDVI, MSAVI, NDWI and NDBI) were used to determine the optimal synthesis time window for Sentinel-2 images. Seven experimental groups, including 14 experimental schemes based on the rectangular tile classification model and the traditional global classification model, were designed. By applying the rectangular tile classification model and Sentinel-integrated images, we successfully identified and extracted grasslands. The results showed the integration of vegetation index features and texture features improved the accuracy of grassland mapping. The overall accuracy of the Sentinel-integrated images from EXP7-2 was 88.23%, which was higher than the accuracy of the single sensor Sentinel-1A (53.52%) in EXP2-2 and Sentinel-2 (86.53%) in EXP5-2. In all seven experimental groups, the rectangular tile classification model was found to improve overall accuracy (OA) by 1.20% to 13.99% compared to the traditional global classification model. This paper presents novel perspectives and guidance for improving the accuracy of remote sensing mapping for land cover classification in arid zones with highly diverse landscapes. The study presents a flexible and scalable model within the Google Earth Engine framework, which can be readily customized and implemented in various geographical locations and time periods.

Mapping burned areas in Thailand using Sentinel-2 imagery and OBIA techniques.

Monitoring burned areas in Thailand and other tropical countries during the post-harvest season is becoming increasingly important. High-resolution remote sensing data from Sentinel-2 satellites, which have a short revisit time, is ideal for accurately and efficiently mapping burned regions. However, automating the mapping of agriculture residual on a national scale is challenging due to the volume of information and level of detail involved. In this study, a Sentinel-2A Level-1C Multispectral Instrument image (MSI) from February 27, 2018 was combined with object-based image analysis (OBIA) algorithms to identify burned areas in Mae Chaem, Chom Thong, Hod, Mae Sariang, and Mae La Noi Districts in Chiang Mai, Thailand. OBIA techniques were used to classify forest, agricultural, water bodies, newly burned, and old burned regions. The segmentation scale parameter value of 50 was obtained using only the original Sentinel-2A band in red, green, blue, near infrared (NIR), and Normalized Difference Vegetation Index (NDVI). The accuracy of the produced maps was assessed using an existing burned area dataset, and the burned area identified through OBIA was found to be 85.2% accurate compared to 500 random burned points from the dataset. These results suggest that the combination of OBIA and Sentinel-2A with a 10 m spatial resolution is very effective and promising for the process of burned area mapping.

A comparative study of satellite altimetry-based and DEM-based methods for estimating lake water volume changes.

This study compared two different methods, the satellite altimetry-based and DEM (digital elevation model)-based, for estimating lake water volume changes. We focused on 34 lakes in China as the testing sites to compare the two methods for lake water volume changes from 2005 to 2020. The satellite altimetry-based method used water levels provided by the DAHITI (Database for Hydrological Time Series of Inland Waters) data and surface areas derived from Landsat imagery. The DEM-based method used the SRTM DEM data in combination with Landsat-derived lake extents. Our results showed a high degree of consistency in lake water volume changes estimated between the two methods (R2 > 0.90), but each method has its limitations. In terms of temporal coverage, the satellite altimetry-based method with the DAHITI data is limited by missing water level data in certain periods. The performance of the DEM-based method in extracting lake shore boundaries in regions with flat terrains (slope <1.5°) is not satisfactory. The DEM-based method has complete regional applicability (100%) in the Tibetan Plateau (TP) Lake Region, yet its effectiveness drops significantly in the Xinjiang and Eastern China Plain Lake Regions, with applicability rates of 50 and 40%, respectively.

A straightforward approach for the rapid detection of red Noctiluca scintillans blooms from satellite imagery.

Red Noctiluca scintillans (RNS), a prominent species of dinoflagellate known for its conspicuous size and ability to form blooms, exhibits heterotrophic behavior and functions as a microzooplankton grazer within the marine food web. In this study, a straightforward technique referred to as the blue-green index (BGI) has been introduced for the purpose of distinguishing and discerning RNS from neighboring waters, owing to its pronounced absorption in the blue-green spectral range. This method has been applied across a range of satellite imagery, encompassing both multi-spectral and hyperspectral sensors. The study delved into three instances of bloom occurrences caused by RNS: firstly, in November 2014 and April 2022 off the western coast of Guangdong, and secondly, in February 2021 within the Beibu Gulf. The notable bloom event in the Beibu Gulf during February 2021 extended across an expansive area totaling 6933.5 km2. The motion speed and direction of the RNS bloom patches were also derived from successive satellite images. The recently introduced BGI method demonstrates insensitivity to suspended sediment, though its successful application necessitates accurate atmospheric correction. Subsequent efforts will involve the quantification of RNS blooms in a more precise manner, utilizing hyperspectral satellite data grounded in optimized band configurations.

Retrieval of high-resolution aerosol optical depth (AOD) using Landsat 8 imageries over different LULC classes over a city along Indo-Gangetic Plain, India.

Aerosol optical depth (AOD) serves as a crucial indicator for assessing regional air quality. To address regional and urban pollution issues, there is a requirement for high-resolution AOD products, as the existing data is of very coarse resolution. To address this issue, we retrieved high-resolution AOD over Kanpur (26.4499°N, 80.3319°E), located in the Indo-Gangetic Plain (IGP) region using Landsat 8 imageries and implemented the algorithm SEMARA, which combines SARA (Simplified Aerosol Retrieval Algorithm) and SREM (Simplified and Robust Surface Reflectance Estimation). Our approach leveraged the green band of the Landsat 8, resulting in an impressive spatial resolution of 30 m of AOD and rigorously validated with available AERONET observations. The retrieved AOD is in good agreement with high correlation coefficients (r) of 0.997, a low root mean squared error of 0.035, and root mean bias of - 4.91%. We evaluated the retrieved AOD with downscaled MODIS (MCD19A2) AOD products across various land classes for cropped and harvested period of agriculture cycle over the study region. It is noticed that over the built-up region of Kanpur, the SEMARA algorithm exhibits a stronger correlation with the MODIS AOD product compared to vegetation, barren areas and water bodies. The SEMARA approach proved to be more effective for AOD retrieval over the barren and built-up land categories for harvested period compared with the cropping period. This study offers a first comparative examination of SEMARA-retrieved high-resolution AOD and MODIS AOD product over a station of IGP.

Urban heat load assessment in Zagreb, Croatia: a multi-scale analysis using mobile measurement and satellite imagery.

A limited number of meteorological stations and sparse data challenge microclimate assessment in urban areas. Therefore, it is necessary to complement these data with additional measurements to achieve a denser spatial coverage, enabling a detailed representation of the city's microclimatic features. In this study, conducted in Zagreb, Croatia, mobile air temperature measurements were utilized and compared with satellite-derived land surface temperature (LST). Here, air temperature measurements were carried out using bicycles and an instrument with a GPS receiver and temperature probe during a heat wave in June 2021, capturing the spatial pattern of air temperature to highlight the city's microclimate characteristics (i.e. urban heat load; UHL) in extremely hot weather conditions. Simultaneously, remotely sensed LST was retrieved from the Landsat-8 satellite. Air temperature measurements were compared to city-specific street type classification, while neighbourhood heat load characteristics were analysed based on local climate zones (LCZ) and LST. Results indicated significant thermal differences between surface types and urban forms and between street types and LCZs. Air temperatures reached up to 35 °C, while LST exceeded 40 °C. City parks, tree-lined streets and areas near blue infrastructure were 1.5-3 °C cooler than densely built areas. Temperature contrasts between LCZs in terms of median LST were more emphasised and reached 9 °C between some classes. These findings highlight the importance of preserving green areas to reduce UHL and enhance urban resilience. Here, exemplified by the city of Zagreb, it has been demonstrated that the use of multiple datasets allows a comprehensive understanding of temperature patterns and their implications for urban climate research.

Evaluating spatially enabled machine learning approaches to depth to bedrock mapping, Alberta, Canada.

Maps showing the thickness of sediments above the bedrock (depth to bedrock, or DTB) are important for many geoscience studies and are necessary for many hydrogeological, engineering, mining, and forestry applications. However, it can be difficult to accurately estimate DTB in areas with varied topography, like lowland and mountainous terrain, because traditional methods of predicting bedrock elevation often underestimate or overestimate the elevation in rugged or incised terrain. Here, we describe a machine learning spatial prediction approach that uses information from traditional digital elevation model derived estimates of terrain morphometry and satellite imagery, augmented with spatial feature engineering techniques to predict DTB across Alberta, Canada. First, compiled measurements of DTB from borehole lithologs were used to train a natural language model to predict bedrock depth across all available lithologs, significantly increasing the dataset size. The combined data were then used for DTB modelling employing several algorithms (XGBoost, Random forests, and Cubist) and spatial feature engineering techniques, using a combination of geographic coordinates, proximity measures, neighbouring points, and spatially lagged DTB estimates. Finally, the results were contrasted with DTB predictions based on modelled relationships with the auxiliary variables, as well as conventional spatial interpolations using inverse-distance weighting and ordinary kriging methods. The results show that the use of spatially lagged variables to incorporate information from the spatial structure of the training data significantly improves predictive performance compared to using auxiliary predictors and/or geographic coordinates alone. Furthermore, unlike some of the other tested methods such as using neighbouring point locations directly as features, spatially lagged variables did not generate spurious spatial artifacts in the predicted raster maps. The proposed method is demonstrated to produce reliable results in several distinct physiographic sub-regions with contrasting terrain types, as well as at the provincial scale, indicating its broad suitability for DTB mapping in general.