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.

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.

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.

Mapping of secondary forest age in China using stacked generalization and Landsat time series.

A national distribution of secondary forest age (SFA) is essential for understanding the forest ecosystem and carbon stock in China. While past studies have mainly used various change detection algorithms to detect forest disturbance, which cannot adequately characterize the entire forest landscape. This study developed a data-driven approach for improving performances of the Vegetation Change Tracker (VCT) and Continuous Change Detection and Classification (CCDC) algorithms for detecting the establishment of forest stands. An ensemble method for mapping national-scale SFA by determining the establishment time of secondary forest stands using change detection algorithms and dense Landsat time series was proposed. A dataset of national secondary forest age for China (SFAC) for 1 to 34 and with a 30-m spatial resolution was produced from the optimal ensemble model. This dataset provides national, continuous spatial SFA information and can improve understanding of secondary forests and the estimation of forest carbon storage in China.

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.

Improvement of pasture biomass modelling using high-resolution satellite imagery and machine learning.

Robust quantification of vegetative biomass using satellite imagery using one or more forms of machine learning (ML) has hitherto been hindered by the extent and quality of training data. Here, we showcase how ML predictive demonstrably improves when additional training data is used. We collated field datasets of pasture biomass obtained via destructive sampling, 'C-Dax' reflective measurements and rising plate meters (RPM) from ten livestock farms across four States in Australia. Remotely sensed data from the Sentinel-2 constellation was used to retrieve aboveground biomass using a novel machine learning paradigm hereafter termed "SPECTRA-FOR" (Spectral Pasture Estimation using Combined Techniques of Random-forest Algorithm for Features Optimisation and Retrieval). Using this framework, we show that the low temporal resolution of Sentinel-2 in high latitude regions with persistent cloud cover leads to extensive gaps between cloud-free images, hindering model performance and, thus, contemporaneous ability to forecast real-time pasture biomass. By leveraging the spectral consistency between Sentinel-2 and Planet Lab SuperDove to overcome this limitation, we used ten spectral bands of Sentinel-2, four bands of Sentinel-2 as a proxy for pre-2022 SuperDove (referred to as synthetic SuperDove or SSD), and the actual SuperDove (ASD), given that SuperDove imagery has a higher resolution and more frequent passage compared with Sentinel-2. Using their respective bands as input features to SPECRA-FOR, model performance for the ten bands of Sentinel-2 were R2 = 0.87, root mean squared error (RMSE) of 439 kg DM/ha and mean absolute error (MAE) of 255 kg DM/ha, while that for SSD increased to an R2 of 0.92, RMSE of 346 kg DM/ha and MAE = 208 kg DM/ha. The study revealed the importance of robust data mining, imagery harmonisation and model validation for accurate real-time modelling of pasture biomass with ML.

Satellite imagery as a management tool for monitoring water clarity across freshwater ponds on Cape Cod, Massachusetts.

Water clarity serves as both an indicator and a regulator of biological function in aquatic systems. Large-scale, consistent water clarity monitoring is needed for informed decision-making. Inland freshwater ponds and lakes across Cape Cod, a 100-km peninsula in Massachusetts, are of particular interest for water clarity monitoring. Secchi disk depth (SDD), a common measure of water clarity, has been measured intermittently for over 200 Cape Cod ponds since 2001. Field-measured SDD data were used to estimate SDD from satellite data, leveraging the NASA/USGS Landsat Program and Copernicus Sentinel-2 mission, spanning 1984 to 2022. Random forest machine learning models were generated to estimate SDD from satellite reflectance data and maximum pond depth. Spearman rank correlations (rs) were "strong" for Landsat 5 and 7 (rs = 0.78 and 0.79), and "very strong" for Landsat 8, 9, and Sentinel-2 (rs = 0.83, 0.86, and 0.80). Mean absolute error also indicated strong predictive capacity, ranging from 0.65 to 1.05 m, while average bias ranged from -0.20 to 0.06 m. Long- and recent short-term changes in satellite-estimated SDD were assessed for 193 ponds, selected based on surface area and the availability of maximum pond depth data. Long-term changes between 1984 and 2022 established a retrospective baseline using the Mann-Kendall test for trend and Theil-Sen slope. Generally, long-term water clarity improved across the Cape; 149 ponds indicated increasing water clarity, and 8 indicated deteriorating water clarity. Recent short-term changes between 2021 and 2022 identified ponds that may benefit from targeted management efforts using the Mann-Whitney U test. Between 2021 and 2022, 96 ponds indicated deteriorations in water clarity, and no ponds improved in water clarity. While the 193 ponds analyzed here constitute only one quarter of Cape Cod ponds, they represent 85% of its freshwater surface area, providing the most spatially and temporally comprehensive assessment of Cape Cod ponds to date. Efforts are focused on Cape Cod, but can be applied to other areas given the availability of local field data. This study defines a framework for monitoring and assessing change in satellite-estimated SDD, which is important for both local and regional management and resource prioritization.

From sky to road: Incorporating the satellite imagery into analysis of freight truck-related crash factors.

Freight truck-related crashes in urban contexts have caused significant economic losses and casualties, making it increasingly essential to understand the spatial patterns of such crashes. Limitations regarding data availability have greatly undermined the generalizability and applicability of certain prior research findings. This study explores the potential of emerging geospatial data to delve deeply into the determinants of these incidents with a more generalizable research design. By synergizing high-resolution satellite imagery with refined GIS map data and geospatial tabular data, a rich tapestry of the road environment and freight truck operations emerges. To navigate the challenges of zero-inflated issues of the crash datasets, the Tweedie Gradient Boosting model is adopted. Results reveal a pronounced spatial heterogeneity between highway and urban non-highway road networks in crash determinants. Factors such as freight truck activity, intricate road network patterns, and vehicular densities rise to prominence, albeit with varying degrees of influence across highways and urban non-highway terrains. Results emphasize the need for context-specific interventions for policymakers, encompassing optimized urban planning, infrastructural overhauls, and refined traffic management protocols. This endeavor may not only elevate the academic discourse around freight truck-related crashes but also champion a data-driven approach towards safer road ecosystems for all.

Advancing crop classification in smallholder agriculture: A multifaceted approach combining frequency-domain image co-registration, transformer-based parcel segmentation, and Bi-LSTM for crop classification.

Agricultural Remote Sensing has the potential to enhance agricultural monitoring in smallholder economies to mitigate losses. However, its widespread adoption faces challenges, such as diminishing farm sizes, lack of reliable data-sets and high cost related to commercial satellite imagery. This research focuses on opportunities, practices and novel approaches for effective utilization of remote sensing in agriculture applications for smallholder economies. The work entails insights from experiments using datasets representative of major crops during different growing seasons. We propose an optimized solution for addressing challenges associated with remote sensing-based crop mapping in smallholder agriculture farms. Open source tools and data are used for inter and intra-sensor image registration, with a root mean square error of 0.3 or less. We also propose and emphasize on the use of delineated vegetation parcels through Segment Anything Model for Geospatial (SAM-GEOs). Furthermore a Bidirectional-Long Short-Term Memory-based (Bi-LSTM) deep learning model is developed and trained for crop classification, achieving results with accuracy of more than 94% and 96% for validation sets of two data sets collected in the field, during 2 growing seasons.

One to twelve-month-ahead forecasting of MODIS-derived Qinghai Lake area, using neuro-fuzzy system hybridized by firefly optimization.

Lakes, as the main sources of surface water, are of great environmental and ecological importance and largely affect the climatic conditions of the surrounding areas. Lake area fluctuations are very effective on plant and animal biodiversity in the areas covered. Hence, accurate and reliable forecasts of ​lake area might provide the awareness of water and climate resources and the survival of various species dependent on area fluctuations. Using machine learning methods, the current study numerically predicted area fluctuations of ​China's largest lake, Qinghai, over 1 to 12 months ahead of lead time. To this end, Moderate Resolution Imaging Spectroradiometer (MODIS) sensor images were used to monitor the monthly changes in the area of ​the lake from 2000 to 2021. Predictive inputs included the MODIS-derived lake area time latency specified by the autocorrelation function. The data was divided into two periods of the train (initial 75%) and test (final 25%), and the input combinations were arranged so that the model in the test period could be used to predict 12 scenarios, including forecast horizons for the next 1 to 12 months. The adaptive neuro-fuzzy inference system (ANFIS) was utilized as a predictive model. The firefly algorithm (FA) was also used to optimize ANFIS and improve its accuracy, as a hybrid model ANFIS-FA. Based on evaluation criteria such as root mean square error (RMSE) (477-594 km2) and R2 (88-92%), the results confirmed the acceptable accuracy of the models in all forecast horizons, even long-term horizons (10 months, 11 months, and 12 months). Based on the normalized RMSE criterion (0.095-0.125), the models' performance was reported to be appropriate. Furthermore, the firefly algorithm improved the prediction accuracy of the ANFIS model by an average of 16.9%. In the inter-month survey, the models had fewer forecast errors in the dry months (February-March) than in the wet months (October-November). Using the current method can provide remarkable information about the future state of lakes, which is very important for managers and planners of water resources, environment, and natural ecosystems. According to the results, the current approach is satisfactory in predicting MODIS-derived fluctuations of Qinghai Lake area and has research value for other lakes.

Ground far-red sun-induced chlorophyll fluorescence and vegetation indices in the US Midwestern agroecosystems.

Sun-induced chlorophyll fluorescence (SIF) provides an opportunity to study terrestrial ecosystem photosynthesis dynamics. However, the current coarse spatiotemporal satellite SIF products are challenging for mechanistic interpretations of SIF signals. Long-term ground SIF and vegetation indices (VIs) are important for satellite SIF validation and mechanistic understanding of the relationship between SIF and photosynthesis when combined with leaf- and canopy-level auxiliary measurements. In this study, we present and analyze a total of 15 site-years of ground far-red SIF (SIF at 760 nm, SIF760) and VIs datasets from soybean, corn, and miscanthus grown in the U.S. Corn Belt from 2016 to 2021. We introduce a comprehensive data processing protocol, including different retrieval methods, calibration coefficient adjustment, and nadir SIF footprint upscaling to match the eddy covariance footprint. This long-term ground far-red SIF and VIs dataset provides important and first-hand data for far-red SIF interpretation and understanding the mechanistic relationship between far-red SIF and canopy photosynthesis across various crop species and environmental conditions.

Improving on mapping long-term surface water with a novel framework based on the Landsat imagery series.

Surface water plays a crucial role in the ecological environment and societal development. Remote sensing detection serves as a significant approach to understand the temporal and spatial change in surface water series (SWS) and to directly construct long-term SWS. Limited by various factors such as cloud, cloud shadow, and problematic satellite sensor monitoring, the existent surface water mapping datasets might be short and incomplete due to losing raw information on certain dates. Improved algorithms are desired to increase the completeness and quality of SWS datasets. The present study proposes an automated framework to detect SWS, based on the Google Earth Engine and Landsat satellite imagery. This framework incorporates implementing a raw image filtering algorithm to increase available images, thereby expanding the completeness. It improves OTSU thresholding by replacing anomaly thresholds with the median value, thus enhancing the accuracy of SWS datasets. Gaps caused by Landsat7 ETM + SLC-off are respired with the random forest algorithm and morphological operations. The results show that this novel framework effectively expands the long-term series of SWS for three surface water bodies with distinct geomorphological patterns. The evaluation of confusion matrices suggests the good performance of extracting surface water, with the overall accuracy ranging from 0.96 to 0.97, and user's accuracy between 0.96 and 0.98, producer's accuracy ranging from 0.83 to 0.89, and Matthews correlation coefficient ranging from 0.87 to 0.9 for several spectral water indices (NDWI, MNDWI, ANNDWI, and AWEI). Compared with the Global Reservoirs Surface Area Dynamics (GRSAD) dataset, our constructed datasets promote greater completeness of SWS datasets by 27.01%-91.89% for the selected water bodies. The proposed framework for detecting SWS shows good potential in enlarging and completing long-term global-scale SWS datasets, capable of supporting assessments of surface-water-related environmental management and disaster prevention.

Spatio-temporal correspondence of aerosol optical depth between CMIP6 simulations and MODIS retrievals over India.

In the present work, the aerosol optical depth (AOD) at 550 nm of the moderate resolution imaging spectroradiometer (MODIS) onboard the Terra satellite was utilised to evaluate the AOD simulations of newly emerged general circulation models (GCMs) of coupled model intercomparison project-phase 6 (CMIP6) over the Indian landmass. Further, the AOD from the CMIP6 models has been compared with its previous generation models from CMIP5 to examine the extent of uncertainties in AOD with reference to the MODIS AOD datasets. The evolution of aerosols over India using the different shared socioeconomic pathways (SSPs) has also been studied till the year 2050. The results show that the CMIP5 and CMIP6 models underestimated the mean annual AOD of the Indian region as a whole. A multi-model mean (MMM) of thirteen GCMs from CMIP6 showed an underestimation of AOD by 40 to 60% over the Indo-Gangetic plains, while an overestimation of 60 to 80% in AOD was observed over the Peninsular and Central Indian regions in comparison with MODIS for the study period of 2001 to 2014. In future simulations, the pathway SSP370 has shown a significant increasing trend of AOD whereas SSP126 and SSP585 have shown significant decreasing trends of AOD by the year 2050. In the future, the changes in the AOD will mainly be contributed by the anthropogenic aerosols (AOA, BC, and Sulphates) emissions in all SSPs. The large bias of MMM with the MODIS requires further research in terms of analysing the accuracy of emission datasets that have been used to simulate the AODs by the CMIP6 models over the Indian region.

ENVINet5 deep learning change detection framework for the estimation of agriculture variations during 2012-2023 with Landsat series data.

Remote sensing is one of the most important methods for analysing the multitemporal changes over a certain period. As a cost-effective way, remote sensing allows the long-term analysis of agricultural land by collecting satellite imagery from different satellite missions. Landsat is one of the longest-running world missions which offers a moderate-resolution earth observation dataset. Land surface mapping and monitoring are generally performed by incorporating classification and change detection models. In this work, a deep learning-based change detection (DCD) algorithm has been proposed to detect long-term agricultural changes using the Landsat series datasets (i.e., Landsat-7, Landsat-8, and Landsat-9) during the period 2012 to 2023. The proposed algorithm extracts the features from satellite data according to their spectral and geographic characteristics and identifies seasonal variability. The DCD integrates the deep learning-based (Environment for visualizing images) ENVI Net-5 classification model and posterior probability-based post-classification comparison-based change detection model (PCD). The DCD is capable of providing seasonal variations accurately with distinct Landsat series dataset and promises to use higher resolution dataset with accurate results. The experimental result concludes that vegetation has decreased from 2012 to 2023, while build-up land has increased up to 88.22% (2012-2023) for Landsat-7 and Landsat-8 datasets. On the other side, degraded area includes water (3.20-0.05%) and fallow land (1-0.59%). This study allows the identification of crop growth, crop yield prediction, precision farming, and crop mapping.

Next-level vegetation health index forecasting: A ConvLSTM study using MODIS Time Series.

The Vegetation Health Index (VHI) is a metric used to assess the health and condition of vegetation, based on satellite-derived data. It offers a comprehensive indicator of stress or vigor, commonly used in agriculture, ecology, and environmental monitoring for forecasting changes in vegetation health. Despite its advantages, there are few studies on forecasting VHI as a future projection, particularly using up-to-date and effective machine learning methods. Hence, the primary objective of this study is to forecast VHI values by utilizing remotely sensed images. To achieve this objective, the study proposes employing a combined Convolutional Neural Network (CNN) and a specific type of Recurrent Neural Network (RNN) called Long Short-Term Memory (LSTM), known as ConvLSTM. The VHI time series images are calculated based on the Normalized Difference Vegetation Index (NDVI) and Land Surface Temperature (LST) data obtained from the Moderate Resolution Imaging Spectroradiometer (MODIS) aboard the Terra and Aqua satellites. In addition to the traditional image-based calculation, the study suggests using global minimum and global maximum values (global scale) of NDVI and LST time series for calculating the VHI. The results of the study showed that the ConvLSTM with a 1-layer structure generally provided better forecasts than 2-layer and 3-layer structures. The average Root Mean Square Error (RMSE) values for the 1-step, 2-step, and 3-step ahead VHI forecasts were 0.025, 0.026, and 0.026, respectively, with each step representing an 8-day forecast horizon. Moreover, the proposed global scale model using the applied ConvLSTM structures outperformed the traditional VHI calculation method.

Exploring machine learning and statistical approach techniques for landslide susceptibility mapping in Siwalik Himalayan Region using geospatial technology.

Landslides are a natural threat that poses a severe risk to human life and the environment. In the Kumaon mountains region in Uttarakhand (India), Nainital is among the most vulnerable areas prone to landslides inflicting harm to livelihood and civilization due to frequent landslides. Developing a landslide susceptibility map (LSM) in this Nainital area will help alleviate the probability of landslide occurrence. GIS and statistical-based approaches like the certainty factor (CF), information value (IV), frequency ratio (FR) and logistic regression (LR) are used for the assessment of LSM. The landslide inventories were prepared using topography, satellite imagery, lithology, slope, aspect, curvature, soil, land use and land cover, geomorphology, drainage density and lineament density to construct the geodatabase of the elements affecting landslides. Furthermore, the receiver operating characteristic (ROC) curve was used to check the accuracy of the predicting model. The results for the area under the curves (AUCs) were 87.8% for logistic regression, 87.6% for certainty factor, 87.4% for information value and 84.8% for frequency ratio, which indicates satisfactory accuracy in landslide susceptibility mapping. The present study perfectly combines GIS and statistical approaches for mapping landslide susceptibility zonation. Regional land use planners and natural disaster management will benefit from the proposed framework for landslide susceptibility maps.

A Bayesian model for predicting monthly fire frequency in Kenya.

This study presents a comprehensive analysis of historical fire and climatic data to estimate the monthly frequency of vegetation fires in Kenya. This work introduces a statistical model that captures the behavior of fire count data, incorporating temporal explanatory factors and emphasizing the predictive significance of maximum temperature and rainfall. By employing Bayesian approaches, the paper integrates literature information, simulation studies, and real-world data to enhance model performance and generate more precise prediction intervals that encompass actual fire counts. To forecast monthly fire occurrences aggregated from the Moderate Resolution Imaging Spectroradiometer (MODIS) data in Kenya (2000-2018), the study utilizes maximum temperature and rainfall values derived from global GeoTiff (.tif) files sourced from the WorldClim database. The evaluation of the widely used Negative Binomial (NB) model and the proposed Bayesian Negative Binomial (BNB) model reveals the superiority of the latter in accounting for seasonal patterns and long-term trends. The simulation results demonstrate that the BNB model outperforms the NB model in terms of Root Mean Square Error (RMSE), and Mean Absolute Scaled Error (MASE) on both training and testing datasets. Furthermore, when applied to real data, the Bayesian Negative Binomial model exhibits better performance on the test dataset, showcasing lower RMSE (163.22 vs. 166.67), lower MASE (1.12 vs. 1.15), and reduced bias (-2.52% vs. -2.62%) compared to the NB model. The Bayesian model also offers prediction intervals that closely align with actual predictions, indicating its flexibility in forecasting the frequency of monthly fires. These findings underscore the importance of leveraging past data to forecast the future behavior of the fire regime, thus providing valuable insights for fire control strategies in Kenya. By integrating climatic factors and employing Bayesian modeling techniques, the study contributes to the understanding and prediction of vegetation fires, ultimately supporting proactive measures in mitigating their impact.

Satellite mapping reveals extensive industrial activity at sea.

The world's population increasingly relies on the ocean for food, energy production and global trade1-3, yet human activities at sea are not well quantified4,5. We combine satellite imagery, vessel GPS data and deep-learning models to map industrial vessel activities and offshore energy infrastructure across the world's coastal waters from 2017 to 2021. We find that 72-76% of the world's industrial fishing vessels are not publicly tracked, with much of that fishing taking place around South Asia, Southeast Asia and Africa. We also find that 21-30% of transport and energy vessel activity is missing from public tracking systems. Globally, fishing decreased by 12 ± 1% at the onset of the COVID-19 pandemic in 2020 and had not recovered to pre-pandemic levels by 2021. By contrast, transport and energy vessel activities were relatively unaffected during the same period. Offshore wind is growing rapidly, with most wind turbines confined to small areas of the ocean but surpassing the number of oil structures in 2021. Our map of ocean industrialization reveals changes in some of the most extensive and economically important human activities at sea.

Monitoring of wetland turbidity using multi-temporal Landsat-8 and Landsat-9 satellite imagery in the Bisalpur wetland, Rajasthan, India.

Satellite imagery has emerged as the predominant method for performing spatial and temporal water quality analyses on a global scale. This study employs remote sensing techniques to monitor the water quality of the Bisalpur wetland during both the pre and post-monsoon seasons in 2013 and 2022. The study aims to investigate the prospective use of Landsat-8 (L8) and Landsat-9 (L9) data acquired from the Operational Land Imager (OLI) and Thermal Infrared Sensor (TIRS) for the temporal monitoring of turbidity. Concurrently, the study examines the relationship of turbidity with water surface temperature (WST) and chlorophyll-a (Chl-a) concentrations. We utilized visible and near-infrared (NIR) bands to conduct a single-band spectral response analysis of wetland turbidity. The results reveal a notable increase in turbidity concentration in May 2022, as this timeframe recorded the highest reflectance (0.28) in the NIR band. Additionally, the normalized difference turbidity index (NDTI) formula was used to assess the overall turbidity levels in the wetland. The results indicated that the highest concentration was observed in May 2013, with a value of 0.37, while the second-highest concentration was recorded in May 2022, with a value of 0.25. The WST was calculated using thermal band-10 in conjunction with Chlorophyll-a, utilizing the normalized difference chlorophyll index (NDCI). The regression analysis shows a positive correlation between turbidity and WST, as indicated by R2 values of 0.41 in May 2013 and 0.40 in May 2022. Furthermore, a robust positive relationship exists between turbidity and Chl-a, with a high R2 value of 0.71 in May 2022. These findings emphasize the efficacy of the L8 and L9 datasets for conducting temporal analyses of wetland turbidity, WST, and Chl-a. Additionally, this research underscores the critical role of satellite imagery in assessing and managing water quality, particularly in situations where in-situ data is lacking.

Relationship between floating marine debris accumulation and coastal fronts in the Northeast coast of the USA.

Floating marine debris (FMD) is one of the world's most concerning issues due to its potential impact on biodiversity, communities, and ecosystem services. FMD transport and concentrations are driven by fronts, generated by oceanographic processes, and the accumulation of FMD has been reported in gyres, eddies, tidal fronts, salinity fronts, and coastal fronts. This study explores the relationship between fronts and FMD accumulation in the Gulf of Maine (GoM) and the surrounding coastal areas (USA). Frontal edge detection algorithms were applied to sea surface temperature (SST) imagery from the Moderate-resolution Imaging Spectroradiometer (MODIS) between 2002 and 2012. Frontal location is spatially correlated with FMD concentrations collected by the Sea Education Association. Higher concentrations of FMD are associated with frontal frequencies (FF) of 5-10 %. FMD is trapped between fronts and the coastline in accumulation zones. These results highlight the need to consider coastal FMD hotspots, given these are areas of high biodiversity value.