The MODIS land surface temperature (LST) product is one of the most widely used data sources to study the climate and energy-water cycle at a global scale. However, the large number of invalid values caused by cloud cover limits the wide application of the MODIS LST. In this study, a two-step improved similar pixels (TISP) method was proposed for cloudy sky LST reconstruction. The TISP method was validated using a temperature-based method over various land cover types. The ground measurements were collected at fifteen stations from 2013 to 2018 during the Heihe Watershed Allied Telemetry Experimental Research (HiWATER) field campaign in China. The estimated theoretical clear-sky temperature indicates that clouds cool the land surface during the daytime and warm it at nighttime. For bare land, the surface temperature shows a clear seasonal trend and very similar across stations, with a cooling amplitude of 4.14 K in the daytime and a warming amplitude of 3.99 K at nighttime, as a yearly average. The validation result showed that the reconstructed LST is highly consistent with in situ measurements and comparable with MODIS LST validation accuracy, with a mean bias of 0.15 K at night (−0.43 K in the day), mean RMSE of 2.91 K at night (4.41 K in the day), and mean R² of 0.93 at night (0.90 in the day). The developed method maximizes the potential of obtaining quality MODIS LST retrievals, ancillary data, and in situ observations, and the results show high accuracy for most land cover types. Full article

The results of earthquake prediction largely depend on the quality of data and the methods of their joint processing. At present, for a number of regions, it is possible, in addition to data from earthquake catalogs, to use space geodesy data obtained with the help of GPS. The purpose of our study is to evaluate the efficiency of using the time series of displacements of the Earth’s surface according to GPS data for the systematic prediction of earthquakes. The criterion of efficiency is the probability of successful prediction of an earthquake with a limited size of the alarm zone. We use a machine learning method, namely the method of the minimum area of alarm, to predict earthquakes with a magnitude greater than 6.0 and a hypocenter depth of up to 60 km, which occurred from 2016 to 2020 in Japan, and earthquakes with a magnitude greater than 5.5. and a hypocenter depth of up to 60 km, which happened from 2013 to 2020 in California. For each region, we compare the following results: random forecast of earthquakes, forecast obtained with the field of spatial density of earthquake epicenters, forecast obtained with spatio-temporal fields based on GPS data, based on seismological data, and based on combined GPS data and seismological data. The results confirm the effectiveness of using GPS data for the systematic prediction of earthquakes. Full article

Globally, major cities are experiencing fast settlement growth, which threatens the equilibrium of socio-ecosystems. In Pakistan, Abbottabad city in particular is experiencing fast urban growth. The main source of daily water usage for the population in these types of cities is groundwater (tube–wells). Excessive pumping and the high need for ground water for the local community are affecting the subsurface sustainability. In this study, the persistent scatterer interferometry synthetic aperture radar (PSInSAR) technique with synthetic aperture radar (SAR) images acquired from the Sentinel-1 were used to monitor ground subsidence in Abbottabad City, Northern Pakistan. To estimate the ground subsidence in Abbottabad City, SARPROZ software was employed to process a series of Sentinel-1 images, acquired from March 2017 to September 2019, along both descending and ascending orbit tracks. The subsidence observed in the results shows a significant increase from 2017 to 2019. The subsidence map shows that, during 2017, the subsidence was −30 mm/year and about −85 mm/year in 2018. While during 2019, the subsidence reached −150 mm/year. Thus, it has seen that, in the study area, the subsidence during these years increased with mean subsidence 60 mm/year. The overall trend of subsidence showed considerably high values in the center of the city, while areas away from the center of the city experienced low subsidence. Overall, the adopted methodology can be used successfully for detecting, mapping, and monitoring land surfaces vulnerable to subsidence. This will facilitate efficient planning, designing of surface infrastructure, and mitigation management of subsidence-induced hazards. Full article

When sufficient time-series images and training data are unavailable for crop classification, features extracted from convolutional neural network (CNN)-based representative learning may not provide useful information to discriminate crops with similar spectral characteristics, leading to poor classification accuracy. In particular, limited input data are the main obstacles to obtain reliable classification results for early crop mapping. This study investigates the potential of a hybrid classification approach, i.e., CNN-random forest (CNN-RF), in the context of early crop mapping, that combines the automatic feature extraction capability of CNN with the superior discrimination capability of an RF classifier. Two experiments on incremental crop classification with unmanned aerial vehicle images were conducted to compare the performance of CNN-RF with that of CNN and RF with respect to the length of the time-series and training data sizes. When sufficient time-series images and training data were used for the classification, the accuracy of CNN-RF was slightly higher or comparable with that of CNN. In contrast, when fewer images and the smallest training data were used at the early crop growth stage, CNN-RF was substantially beneficial and the overall accuracy increased by maximum 6.7%p and 4.6%p in the two study areas, respectively, compared to CNN. This is attributed to its ability to discriminate crops from features with insufficient information using a more sophisticated classifier. The experimental results demonstrate that CNN-RF is an effective classifier for early crop mapping when only limited input images and training samples are available. Full article

Accurate phenological information is essential for monitoring crop development, predicting crop yield, and enhancing resilience to cope with climate change. This study employed a curve-change-based dynamic threshold approach on NDVI (Normalized Differential Vegetation Index) time series to detect the planting and harvesting dates for corn and soybean in Kentucky, a typical climatic transition zone, from 2000 to 2018. We compared satellite-based estimates with ground observations and performed trend analyses of crop phenological stages over the study period to analyze their relationships with climate change and crop yields. Our results showed that corn and soybean planting dates were delayed by 0.01 and 0.07 days/year, respectively. Corn harvesting dates were also delayed at a rate of 0.67 days/year, while advanced soybean harvesting occurred at a rate of 0.05 days/year. The growing season length has increased considerably at a rate of 0.66 days/year for corn and was shortened by 0.12 days/year for soybean. Sensitivity analysis showed that planting dates were more sensitive to the early season temperature, while harvesting dates were significantly correlated with temperature over the entire growing season. In terms of the changing climatic factors, only the increased summer precipitation was statistically related to the delayed corn harvesting dates in Kentucky. Further analysis showed that the increased corn yield was significantly correlated with the delayed harvesting dates (1.37 Bu/acre per day) and extended growing season length (1.67 Bu/acre per day). Our results suggested that seasonal climate change (e.g., summer precipitation) was the main factor influencing crop phenological trends, particularly corn harvesting in Kentucky over the study period. We also highlighted the critical role of changing crop phenology in constraining crop production, which needs further efforts for optimizing crop management practices. Full article

Intertidal seagrass plays a vital role in estimating the overall health and dynamics of coastal environments due to its interaction with tidal changes. However, most seagrass habitats around the globe have been in steady decline due to human impacts, disturbing the already delicate balance in the environmental conditions that sustain seagrass. Miniaturization of multi-spectral sensors has facilitated very high resolution mapping of seagrass meadows, which significantly improves the potential for ecologists to monitor changes. In this study, two analytical approaches used for classifying intertidal seagrass habitats are compared—Object-based Image Analysis (OBIA) and Fully Convolutional Neural Networks (FCNNs). Both methods produce pixel-wise classifications in order to create segmented maps. FCNNs are an emerging set of algorithms within Deep Learning. Conversely, OBIA has been a prominent solution within this field, with many studies leveraging in-situ data and multiresolution segmentation to create habitat maps. This work demonstrates the utility of FCNNs in a semi-supervised setting to map seagrass and other coastal features from an optical drone survey conducted at Budle Bay, Northumberland, England. Semi-supervision is also an emerging field within Deep Learning that has practical benefits of achieving state of the art results using only subsets of labelled data. This is especially beneficial for remote sensing applications where in-situ data is an expensive commodity. For our results, we show that FCNNs have comparable performance with the standard OBIA method used by ecologists. Full article

European aspen (Populus tremula L.) is a keystone species for biodiversity of boreal forests. Large-diameter aspens maintain the diversity of hundreds of species, many of which are threatened in Fennoscandia. Due to a low economic value and relatively sparse and scattered occurrence of aspen in boreal forests, there is a lack of information of the spatial and temporal distribution of aspen, which hampers efficient planning and implementation of sustainable forest management practices and conservation efforts. Our objective was to assess identification of European aspen at the individual tree level in a southern boreal forest using high-resolution photogrammetric point cloud (PPC) and multispectral (MSP) orthomosaics acquired with an unmanned aerial vehicle (UAV). The structure-from-motion approach was applied to generate RGB imagery-based PPC to be used for individual tree-crown delineation. Multispectral data were collected using two UAV cameras: Parrot Sequoia and MicaSense RedEdge-M. Tree-crown outlines were obtained from watershed segmentation of PPC data and intersected with multispectral mosaics to extract and calculate spectral metrics for individual trees. We assessed the role of spectral data features extracted from PPC and multispectral mosaics and a combination of it, using a machine learning classifier—Support Vector Machine (SVM) to perform two different classifications: discrimination of aspen from the other species combined into one class and classification of all four species (aspen, birch, pine, spruce) simultaneously. In the first scenario, the highest classification accuracy of 84% (F1-score) for aspen and overall accuracy of 90.1% was achieved using only RGB features from PPC, whereas in the second scenario, the highest classification accuracy of 86 % (F1-score) for aspen and overall accuracy of 83.3% was achieved using the combination of RGB and MSP features. The proposed method provides a new possibility for the rapid assessment of aspen occurrence to enable more efficient forest management as well as contribute to biodiversity monitoring and conservation efforts in boreal forests. Full article

Rangelands provide significant socioeconomic and environmental benefits to humans. However, climate variability and anthropogenic drivers can negatively impact rangeland productivity. The main goal of this study was to investigate structural and productivity changes in rangeland ecosystems in New Mexico (NM), in the southwestern United States of America during the 1984–2015 period. This goal was achieved by applying the time series segmented residual trend analysis (TSS-RESTREND) method, using datasets of the normalized difference vegetation index (NDVI) from the Global Inventory Modeling and Mapping Studies and precipitation from Parameter elevation Regressions on Independent Slopes Model (PRISM), and developing an assessment framework. The results indicated that about 17.6% and 12.8% of NM experienced a decrease and an increase in productivity, respectively. More than half of the state (55.6%) had insignificant change productivity, 10.8% was classified as indeterminant, and 3.2% was considered as agriculture. A decrease in productivity was observed in 2.2%, 4.5%, and 1.7% of NM’s grassland, shrubland, and ever green forest land cover classes, respectively. Significant decrease in productivity was observed in the northeastern and southeastern quadrants of NM while significant increase was observed in northwestern, southwestern, and a small portion of the southeastern quadrants. The timing of detected breakpoints coincided with some of NM’s drought events as indicated by the self-calibrated Palmar Drought Severity Index as their number increased since 2000s following a similar increase in drought severity. Some breakpoints were concurrent with some fire events. The combination of these two types of disturbances can partly explain the emergence of breakpoints with degradation in productivity. Using the breakpoint assessment framework developed in this study, the observed degradation based on the TSS-RESTREND showed only 55% agreement with the Rangeland Productivity Monitoring Service (RPMS) data. There was an agreement between the TSS-RESTREND and RPMS on the occurrence of significant degradation in productivity over the grasslands and shrublands within the Arizona/NM Tablelands and in the Chihuahua Desert ecoregions, respectively. This assessment of NM’s vegetation productivity is critical to support the decision-making process for rangeland management; address challenges related to the sustainability of forage supply and livestock production; conserve the biodiversity of rangelands ecosystems; and increase their resilience. Future analysis should consider the effects of rising temperatures and drought on rangeland degradation and productivity. Full article

Wastewater treatment plants (WWTPs) are sources of greenhouse gases, hazardous air pollutants and offensive odors. These emissions can have negative repercussions in and around the plant, degrading the quality of life of surrounding neighborhoods, damaging the environment, and reducing employee’s overall job satisfaction. Current monitoring methodologies based on fixed gas detectors and sporadic olfactometric measurements (human panels) do not allow for an accurate spatial representation of such emissions. In this paper we use a small drone equipped with an array of electrochemical and metal oxide (MOX) sensors for mapping odorous gases in a mid-sized WWTP. An innovative sampling system based on two (10 m long) flexible tubes hanging from the drone allowed near-source sampling from a safe distance with negligible influence from the downwash of the drone’s propellers. The proposed platform is very convenient for monitoring hard-to-reach emission sources, such as the plant’s deodorization chimney, which turned out to be responsible for the strongest odor emissions. The geo-localized measurements visualized in the form of a two-dimensional (2D) gas concentration map revealed the main emission hotspots where abatement solutions were needed. A principal component analysis (PCA) of the multivariate sensor signals suggests that the proposed system can also be used to trace which emission source is responsible for a certain measurement. Full article

Nowadays, in the field of data mining, time series data analysis is a very important and challenging subject. This is especially true for time series remote sensing classification. The classification of remote sensing images is an important source of information for land resource planning and management, rational development, and protection. Many experts and scholars have proposed various methods to classify time series data, but when these methods are applied to real remote sensing time series data, there are some deficiencies in classification accuracy. Based on previous experience and the processing methods of time series in other fields, we propose a neural network model based on a self-attention mechanism and time sequence enhancement to classify real remote sensing time series data. The model is mainly divided into five parts: (1) memory feature extraction in subsequence blocks; (2) self-attention layer among blocks; (3) time sequence enhancement; (4) spectral sequence relationship extraction; and (5) a simplified ResNet neural network. The model can simultaneously consider the three characteristics of time series local information, global information, and spectral series relationship information to realize the classification of remote sensing time series. Good experimental results have been obtained by using our model. Full article

Understanding the response of vegetation and ecosystem resilience to climate variability and drought conditions is essential for ecosystem planning and management. In this study, we assessed the vegetation changes and ecosystem resilience in the Horn of Africa (HOA) since 2000 and detected their drivers based mainly on analysis of the Moderate Resolution Imaging Spectroradiometer (MODIS) products. We found that the annual and seasonal trends of NDVI (Normalized Difference Vegetation Index) generally increased during the last two decades over the Horn of Africa particularly in western parts of Ethiopia and Kenya. The weakest annual and seasonal NDVI trends were observed over the grassland cover and tropical arid agroecological zones. The NDVI variation negatively correlated with Land Surface Temperature (LST) and positively correlated with precipitation at a significant level (p < 0.05) account for 683,197 km² and 533,385 km² area, respectively. The ecosystem Water Use Efficiency (eWUE) showed overall increasing trends with larger values for the grassland biome. The precipitation had the most significant effect on eWUE variation compared to LST and annual SPEI (Standardized Evapotranspiration Index). There were about 54.9% of HOA resilient to drought disturbance, whereas 32.6% was completely not-resilient. The ecosystems in the humid agroecological zones, the cropland, and wetland were slightly not-resilient to severe drought conditions in the region. This study provides useful information for policy makers regarding ecosystem and dryland management in the context of climate change at both national and regional levels. Full article

Atmospheric transmissivity (τ) is a critical factor in climatology, which affects surface energy balance, measured at a limited number of meteorological stations worldwide. With the limited availability of meteorological datasets in remote areas across different climatic regions, estimation of τ is becoming a challenging task for adequate hydrological, climatic, and crop modeling studies. The availability of solar radiation data is comparatively less accessible on a global scale than the temperature and precipitation datasets, which makes it necessary to develop methods to estimate τ. Most of the previous studies provided region specific datasets of τ, which usually provide local assessments. Hence, there is a necessity to give the empirical models for τ estimation on a global scale that can be easily assessed. This study presents the analysis of the τ relationship with varying geographic features and climatic factors like latitude, aridity index, cloud cover, precipitation, temperature, diurnal temperature range, and elevation. In addition to these factors, the applicability of these relationships was evaluated for different climate types. Thus, empirical models have been proposed for each climate type to estimate τ by using the most effective factors such as cloud cover and aridity index. The cloud cover is an important yet often overlooked factor that can be used to determine the global atmospheric transmissivity. The empirical relationship and statistical indicator provided the best performance in equatorial climates as the coefficient of determination (r²) was 0.88 relatively higher than the warm temperate (r² = 0.74) and arid regions (r² = 0.46). According to the results, it is believed that the analysis presented in this work is applicable for estimating the τ in different ecosystems across the globe. Full article

Assessing the spatial dynamics of soil organic carbon (SOC) is essential for carbon monitoring. Since variability of SOC is mainly attributed to biophysical land surface variables, integrating a compressive set of such indices may support the pursuit of an optimum set of predictor variables. Therefore, this study was aimed at predicting the spatial distribution of SOC in relation to remotely sensed variables and other covariates. Hence, the land surface variables were combined from remote sensing, topographic, and soil spectral sources. Moreover, the most influential variables for prediction were selected using the random forest (RF) and classification and regression tree (CART). The results indicated that the RF model has good prediction performance with corresponding R² and root-mean-square error (RMSE) values of 0.96 and 0.91 mg·g⁻¹, respectively. The distribution of SOC content showed variability across landforms (CV = 78.67%), land use (CV = 93%), and lithology (CV = 64.67%). Forestland had the highest SOC (13.60 mg·g⁻¹) followed by agriculture (10.43 mg·g⁻¹), urban (9.74 mg·g⁻¹), and water body (4.55 mg·g⁻¹) land uses. Furthermore, soils developed in bauxite and laterite lithology had the highest SOC content (14.69 mg·g⁻¹). The SOC content was remarkably lower in soils developed in sandstones; however, the values obtained in soils from the rest of the lithologies could not be significantly differentiated. The mean SOC concentration was 11.70 mg·g⁻¹, where the majority of soils in the study area were classified as highly humus and extremely humus. The soils with the highest SOC content (extremely humus) were distributed in the mountainous regions of the study area. The biophysical land surface indices, brightness removed vegetation indices, topographic indices, and soil spectral bands were the most influential predictors of SOC in the study area. The spatial variability of SOC may be influenced by landform, land use, and lithology of the study area. Remotely sensed predictors including land moisture, land surface temperature, and built-up indices added valuable information for the prediction of SOC. Hence, the land surface indices may provide new insights into SOC modeling in complex landscapes of warm subtropical urban regions. Full article

The ExoMars Trace Gas Orbiter (TGO)’s Colour and Stereo Surface Imaging System (CaSSIS) provides multi-spectral optical imagery at 4–5 m/pixel spatial resolution. Improving the spatial resolution of CaSSIS images would allow greater amounts of scientific information to be extracted. In this work, we propose a novel Multi-scale Adaptive weighted Residual Super-resolution Generative Adversarial Network (MARSGAN) for single-image super-resolution restoration of TGO CaSSIS images, and demonstrate how this provides an effective resolution enhancement factor of about 3 times. We demonstrate with qualitative and quantitative assessments of CaSSIS SRR results over the Mars2020 Perseverance rover’s landing site. We also show examples of similar SRR performance over 8 science test sites mainly selected for being covered by HiRISE at higher resolution for comparison, which include many features unique to the Martian surface. Application of MARSGAN will allow high resolution colour imagery from CaSSIS to be obtained over extensive areas of Mars beyond what has been possible to obtain to date from HiRISE. Full article

Predicting the spatio-temporal distribution of absorbable heavy metals in soil is needed to identify the potential contaminant sources and develop appropriate management plans to control these hazardous pollutants. Therefore, our aim was to develop a model to predict soil adsorbable heavy metals in arid regions of Iran from 1986 to 2016. Soil adsorbable heavy metals were measured in 201 samples from locations selected using the Latin hypercube sampling method in 2016. A random forest (RF) model was used to determine the relationship between a suite of geospatial predictors derived from remote sensing and digital elevation model data with georeferenced measurements of soil absorbable heavy metals. The trained RF model from 2016 was used to reconstruct the spatial distribution of soil absorbable heavy metals at three historical timesteps (1986, 1999, and 2010). Results indicated that the RF model was effective at predicting the distribution of heavy metals with coefficients of determination of 0.53, 0.59, 0.41, 0.45, and 0.60 for Fe, Mn, Ni, Pb, and Zn, respectively. The predicted maps showed high spatio-temporal variability; for example, there were substantial increases in Pb (the 1.5–2 mg/kg⁻¹ class) where its distribution increased by ~25% from 1988 to 2016—similar trends were observed for the other heavy metals. This study provides insights into the spatio-temporal trends and the potential causes of soil heavy metal contamination to facilitate appropriate planning and management strategies to prevent, control, and reduce the impact of heavy metal contamination in soils. Full article