Search

NASA's Soil Moisture Active Passive (SMAP) was originally designed to combine high-resolution active (radar) and coarse-resolution but highly sensitive passive (radiometer) L-band observations to achieve unprecedented spatial resolution and accuracy for soil moisture retrievals. However, shortly after SMAP was put into orbit, the radar component failed, and the high-resolution capability was lost. In this paper, the integration of an alternative radar sensor with the SMAP radiometer is proposed to enhance soil moisture retrieval capabilities over vegetated areas in the absence of the original high-resolution radar in the SMAP mission. ESA's Sentinel-1A C-band radar was used in this study to enhance the spatial resolution of the SMAP L-band radiometer and to improve soil moisture retrieval accuracy. To achieve this purpose, we downscaled the 9 km radiometer data of the SMAP to 1 km utilizing the Smoothing Filter-based Intensity Modulation (SFIM) method. An Artificial Neural Network (ANN) was then trained to exploit the synergy between the Sentinel-1A radar, SMAP radiometer, and the in situ-measured soil moisture. An analysis of the data obtained for a plant growing season over the Mississippi Delta showed that the VH-polarized Sentinel-1A radar data can yield a coefficient of correlation of 0.81 and serve as a complimentary source to the SMAP radiometer for more accurate and enhanced soil moisture prediction over agricultural fields. [ABSTRACT FROM AUTHOR]

It is a difficult undertaking to reliably estimate global terrestrial evapotranspiration (ET) using the Visible Infrared Imaging Radiometer Suite (VIIRS) at high spatial and temporal scales. We employ deep neural networks (DNN) to enhance the estimation of terrestrial ET on a global scale using satellite data. We accomplish this by merging five algorithms that are process-based and that make use of VIIRS data. These include the Shuttleworth–Wallace dual-source ET method (SW), the Priestley–Taylor-based ET algorithm (PT-JPL), the MOD16 ET product algorithm (MOD16), the modified satellite-based Priestley–Taylor ET algorithm (MS-PT), and the simple hybrid ET algorithm (SIM). We used 278 eddy covariance (EC) tower sites from 2012 to 2022 to validate the DNN approach, comparing it to Bayesian model averaging (BMA), gradient boosting regression tree (GBRT) and random forest (RF). The validation results demonstrate that the DNN significantly improves the accuracy of daily ET estimates when compared to three other merging methods, resulting in the highest average determination coefficients (R2, 0.71), RMSE (21.9 W/m2) and Kling–Gupta efficiency (KGE, 0.83). Utilizing the DNN, we generated a VIIRS ET product with a 500 m spatial resolution for the years 2012–2020. The DNN method serves as a foundational approach in the development of a sustained and comprehensive global terrestrial ET dataset. The basis for characterizing and analyzing global hydrological dynamics and carbon cycling is provided by this dataset. [ABSTRACT FROM AUTHOR]

Accurately mapping lithological features is essential for geological surveys and the exploration of mineral resources. Remote-sensing images have been widely used to extract information about mineralized alteration zones due to their cost-effectiveness and potential for being widely applied. Automated methods, such as machine-learning algorithms, for lithological mapping using satellite imagery have also received attention. This study aims to map lithologies and minerals indirectly through machine-learning algorithms using advanced spaceborne thermal emission and reflection radiometer (ASTER) remote-sensing data. The capabilities of several machine-learning (ML) algorithms were evaluated for lithological mapping, including random forest (RF), support vector machine (SVM), gradient boosting (GB), extreme gradient boosting (XGB), and a deep-learning artificial neural network (ANN). These methods were applied to ASTER imagery of the Sar-Cheshmeh copper mining region of Kerman Province, in southern Iran. First, several spectral features that were extracted from ASTER bands were used as input data. Second, correlation coefficients between the original spectral bands and features were extracted. The importance of the random forest features (RF's feature importance) was subsequently computed, and features with less importance were removed. Finally, the remained features were given to the models as input data in the second scenario. Accuracy assessments were performed for lithological classes in the study region, including Sar-Cheshmeh porphyry, quartz eye, late fine porphyry, hornblende dike, granodiorite, feldspar dike, biotite dike, andesite, and alluvium. The overall accuracy results of lithological mapping showed that ML-based algorithms without feature extraction have the highest accuracy. The overall accuracy percentages for ML-based algorithms without conducting feature extraction were 84%, 85%, 80%, 82%, and 80% for RF, SVM, GB, XGB, and ANN, respectively. The results of this study would be of great interest to geologists for lithological mapping and mineral exploration, particularly for selecting appropriate ML-based techniques to be implemented in similar regions. [ABSTRACT FROM AUTHOR]

Accurate forecasting of fluctuations in groundwater table is crucial for the effective management of regional water resources. This study explores the potential of utilizing remotely sensed satellite data to predict and forecast water table variations. Specifically, two Artificial Neural Network (ANN) models were developed to simulate water table fluctuations at two distinct well sites, namely BA Ea 18 and FR Df 35 in Maryland. One model leveraged the relationship between variations in brightness temperature and water table depth, while the other model was founded on the association between changes in soil moisture and water table depth. These models were trained and validated using recorded water table depths from the aforementioned wells, brightness temperature data acquired from the Advanced Microwave Scanning Radiometer—Earth Observing System (AMSR-E), and soil moisture information generated using the Land Data Assimilation System (LDAS). All models exhibited strong performance in predicting and forecasting water table fluctuations, with root mean square errors ranging from 0.043 m to 0.047 m for a 12-month forecasting horizon. Sensitivity tests revealed that the models displayed greater sensitivity to uncertainties in water table depth compared to uncertainties in both brightness temperature and soil moisture content. This underscores the feasibility of constructing an ANN-based water table prediction model, even in cases where high-resolution remotely sensed data is unavailable. In such situations, the model's efficacy is contingent on the compatibility of the time series trends in data, such as brightness temperature or soil moisture, with those observed at the study site. [ABSTRACT FROM AUTHOR]

The sea surface temperature (SST) is one of the most important parameters that characterize the thermal state of the ocean surface, directly affecting the heat exchange between the ocean and the atmosphere, climate change, and weather generation. Generally, due to factors such as the weather, satellite scanning orbit range, and satellite sensor malfunction, there are large areas of missing satellite remote sensing SST data, greatly reducing data utilization. In this situation, how to use effective data or avenues to rebuild missing SST data has become a research hotspot in the field of ocean remote sensing. Based on the SST data from an FY-3C visible and infrared radiometer with a spatial resolution of 5 km (FY-3C VIRR), an improved data interpolation convolutional autoencoder (I-DINCAE) was used to reconstruct the missing SST data. Through cross-validation, the accuracy of the reconstruction results was quantitatively evaluated with an RMSE of 0.36 °C and an MAE of 0.24 °C. The results showed that the I-DINCAE algorithm outperformed the original DINCAE algorithm greatly. For further optimization, a deep neural network (DNN) was chosen to adjust the error between the reconstructed SST and the in situ data. The RMSE of the final adjusted SST and in situ data is 0.466 °C, and the MAE is 0.296 °C. Compared to the in situ data, the accuracy of the adjusted data has shown a significant improvement over the reconstructed data. This method successfully applies deep-learning technology to the reconstruction of SST data, achieving the full coverage and high accuracy of SST products, which can provide more reliable and complete SST data for marine scientific research. [ABSTRACT FROM AUTHOR]

Gas flaring (GF) has the negative impact on the environment, climate, and human health. So, regular monitoring of flares and quantification of their volume is necessary. Iran has many natural oil/gas processing plants and petrochemical companies which are concentrated in the southern region. Pars Special Economic Energy Zone (PSEEZ) is an industry part with different kinds of active flares, thus a significant potential source of environmental impacts due to gas flaring. Remotely sensed data are used in gas‐flaring detection, volume estimation, and pollution emission. In this study, we applied day/nighttime radiation and air pollutant data to estimate gas flaring volumes. We developed artificial neural network models (ANN) for finding the relationship between the field measurement of GF volume as the dependent variable and shortwave infrared and thermal infrared bands of Landsat 8, M10 band of Visible Infrared Imaging Radiometer Suite, and air pollutant (NO2, CO, O3, and SO2) of TROPOMI as independent variables. Results showed that R2 values were 0.73 for the ANN model from 2018 to 2019. The sensitivity analysis demonstrated that the thermal infrared bands of B10 and B11 of Landsat 8 had the most important role in the estimation of gas flaring volume. In contrast, the SWIR bands of Landsat 8 and all TROPOMI products were insignificant. The findings of this research help to shed light on the use of remotely sensed data in estimating the volume of gas flaring at the regional/global scale by integration of the ANN model. Plain Language Summary: Gas flaring (GF) is an essential process that used to dispose the unwanted gases in oil/gas processing plants and petrochemical companies. Obviously, burning gases has a huge and negative impact on the environment, climate, and human health. So, the best way to manage these effects are monitoring, detecting, characterizing, and estimating the volume of gas flaring. Remote sensing has enough potential to provide the useful data in all parts of the research on GF in industrial areas. In this study, we estimated the volume of gas flaring in one of the gas industries of Iran, the Pars Special Economic Energy Zone (PSEEZ) by using remotely sensed data (B6, B7, B10, B11/landsat8‐ M10/VIIRS‐ NO2, CO, O3, SO2/Sentinel‐5P) and ground data based on two kinds of models, artificial neural network (ANN), and multivariate regression. Since there was a non‐linear relationship between the variables and the volume of gas flaring, the ANN model showed the most acceptable results. Among all the variables, bands 10 and 11 of Landsat 8 played a very important role in estimating the gas flaring volume. Key Points: Air pollutants and remote sensing radiation used for estimation of gas flaring volumeThermal infrared bands of Landsat 8 showed the most important role in GF volume estimationNO2 showed more significant role in GF volume estimation compared to others pollutants [ABSTRACT FROM AUTHOR]

As a global issue, water shortage has attracted much attention from the society. Artificial rain enhancement (ARE) is an effective way to exploit cloud water resources and solve water shortage, but the timing of operation is always a key problem that ARE is facing. The fluctuating properties of water vapor content (WVC) are intricately tied to the choice of operational timing, so accurately predicting the evolution of WVC holds paramount importance when determining the optimal operational timing. However, most of the proposed forecasting methods are limited to simple time series forecasting, and do not pay attention to the complex characteristics of the original data and the shortcomings of a single model prediction. Therefore, the prediction accuracy is difficult to meet the requirements of increasingly refined meteorological services. To tackle this challenge, a new hybrid prediction model, including data reconstruction strategy, benchmark model and improved multi-objective optimization algorithm, is proposed in our research by combining advanced theoretical research of artificial intelligence and data preprocessing ideas. The microwave radiometer WVC observation data at high altitude of Qilian Mountains in China is taken as a case study. By comparing 12 mainstream models, it can be concluded that: The model developed in this study achieves the highest prediction accuracy, and the mean MAPE of the three data sets at 2, 4, 6 and 8 prediction steps is 1.23%, 1.33%, 1.37% and 1.52%, respectively. This result verifies the superiority and practical value of the proposed model in predicting WVC under complex terrain conditions, and provides an excellent solution for accurate prediction of WVC. [ABSTRACT FROM AUTHOR]

The precision monitoring of film-mulched winter wheat growth facilitates field management optimization and further improves yield. Unmanned aerial vehicle (UAV) is an effective tool for crop monitoring at the field scale. However, due to the interference of background effects caused by soil and mulch, achieving accurate monitoring of crop growth in complex backgrounds for UAV remains a challenge. Additionally, the simultaneous inversion of multiple growth parameters helped us to comprehensively monitor the overall crop growth status. This study conducted field experiments including three winter wheat mulching treatments: ridge mulching, ridge–furrow full-mulching, and flat cropping full-mulching. Three machine learning algorithms (partial least squares, ridge regression, and support vector machines) and deep neural network were employed to process the vegetation indices (VIs) feature data, and the residual neural network 50 (ResNet 50) was used to process the image data. Then the two modalities (VI feature data and image data) were fused to obtain a multi-modal fusion (MMF) model. Meanwhile, a film-mulched winter wheat growth monitoring model that simultaneously predicted leaf area index (LAI), aboveground biomass (AGB), plant height (PH), and leaf chlorophyll content (LCC) was constructed by coupling multi-task learning techniques. The results showed that the image-based ResNet 50 outperformed the VI feature-based model. The MMF improved prediction accuracy for LAI, AGB, PH, and LCC with coefficients of determination of 0.73–0.92, mean absolute errors of 0.29–3.89 and relative root mean square errors of 9.48–12.99%. A multi-task MMF model with the same loss weight distribution ([1/4, 1/4, 1/4, 1/4]) achieved comparable accuracy to the single-task MMF model, improving training efficiency and providing excellent generalization to different film-mulched sample areas. The novel technique of the multi-task MMF model proposed in this study provides an accurate and comprehensive method for monitoring the growth status of film-mulched winter wheat. [ABSTRACT FROM AUTHOR]

Data fusion of aerosol optical depth (AOD) datasets from the second generation of the Geostationary Korea Multi-Purpose Satellite (GEO-KOMPSAT-2, GK-2) series was undertaken using both statistical and deep neural network (DNN)-based methods. The GK-2 mission includes an Advanced Meteorological Imager (AMI) aboard GK-2A and a Geostationary Environment Monitoring Spectrometer (GEMS) and Geostationary Ocean Color Imager II (GOCI-II) aboard GK-2B. The statistical fusion method, maximum likelihood estimation (MLE), corrected the bias of each aerosol product by assuming a Gaussian error distribution and accounted for pixel-level uncertainties by weighting the root-mean-square error of each AOD product for every pixel. A DNN-based fusion model was trained to target AErosol RObotic NETwork (AERONET) AOD values using fully connected hidden layers. The MLE and DNN AOD outperformed individual GEMS and AMI AOD datasets in East Asia (R = 0.888; RMSE = - 0.188; MBE = - 0.076; 60.6 % within EE for MLE AOD; R = 0.905; RMSE = 0.161; MBE = - 0.060; 65.6 % within EE for DNN AOD). The selection of AOD around the Korean Peninsula, which incorporates all aerosol products including GOCI-II, resulted in much better results (R = 0.911; RMSE = 0.113; MBE = - 0.047; 73.3 % within EE for MLE AOD; R = 0.912; RMSE = 0.102; MBE = - 0.028; 78.2 % within EE for DNN AOD). The DNN AOD effectively addressed the rapid increase in uncertainty at higher aerosol loadings. Overall, fusion AOD (particularly DNN AOD) showed improvements with less variance and a negative bias. Both fusion algorithms stabilized diurnal error variations and provided additional insights into hourly aerosol evolution. The application of aerosol fusion techniques to future geostationary satellite projects such as Tropospheric Emissions: Monitoring of Pollution (TEMPO), Sentinel-4, and Geostationary Extended Observations (GeoXO) may facilitate the production of high-quality global aerosol data. [ABSTRACT FROM AUTHOR]

This study proposes a novel approach to estimate canopy density in Picea Schrenkiana var. Tianschanica forest sub-compartments by integrating optical and radar satellite data. This effort is aimed at enhancing methodologies for forest resource surveys and monitoring, particularly vital for the sustainable development of semi-arid mountainous areas with fragile ecological environments. The study area is the West Tianshan Mountain Nature Reserve in Xinjiang, which is characterized by its unique dominant tree species, Picea Schrenkiana. A total of 411 characteristic factors were extracted from Gaofen-2 (GF-2) sub-meter optical satellite imagery, Gaofen-3 (GF-3) multi-polarization synthetic aperture radar satellite imagery, and digital elevation model (DEM) data. Consequently, 17 characteristic parameters were selected based on their correlation with canopy density data to construct an estimation model. Three distinct models were developed, including a multiple stepwise regression model (a linear approach), a Back Propagation (BP) neural network model (a neural network-based method), and a Cubist model (a decision tree-based technique). The results indicate that combining optical and radar image characteristics significantly enhances accuracy, with an Average Absolute Percentage Precision (AAPP) value improvement in estimation accuracy from 76.50% (with optical image) and 78.50% (with radar image) to 78.66% (with both). Of the three models, the BP neural network model achieved the highest overall accuracy (79.19%). At the sub-component scale, the BP neural network model demonstrated superior accuracy in low canopy density estimation (75.37%), whereas the Cubist model, leveraging radar image characteristics, excelled in medium density estimations (87.46%). Notably, the integrated Cubist model combining optical and radar data achieved the highest accuracy for high canopy density estimation (89.17%). This study highlights the effectiveness of integrating optical and radar data for precise canopy density assessment, contributing significantly to ecological resource monitoring methodologies and environmental assessments. [ABSTRACT FROM AUTHOR]

As one of the most widely used spread spectrum techniques, the frequency-hopping spread spectrum (FHSS) has been widely adopted in both civilian and military secure communications. In this technique, the carrier frequency of the signal hops pseudo-randomly over a large range, compared to the baseband. To capture an FHSS signal, conventional non-cooperative receivers without knowledge of the carrier have to operate at a high sampling rate covering the entire FHSS hopping range, according to the Nyquist sampling theorem. In this paper, we propose an adaptive compressed method for joint carrier and direction of arrival (DOA) estimations of FHSS signals, enabling subsequent non-cooperative processing. The compressed measurement kernels (i.e., non-zero entries in the sensing matrix) have been adaptively designed based on the posterior knowledge of the signal and task-specific information optimization. Moreover, a deep neural network has been designed to ensure the efficiency of the measurement kernel design process. Finally, the signal carrier and DOA are estimated based on the measurement data. Through simulations, the performance of the adaptively designed measurement kernels is proved to be improved over the random measurement kernels. In addition, the proposed method is shown to outperform the compressed methods in the literature. [ABSTRACT FROM AUTHOR]

Machine learning (ML) has been broadly applied for vadose zone applications in recent years. This article provides a comprehensive review of such developments. ML applications for variables corresponding to different complex vadose zone processes are summarized mostly in a prediction context. By analyzing and assessing these applications, we discovered extensive usages of classic ML models with relatively limited applications of deep learning (DL) approaches in general. We also recognized a lack of benchmark datasets for soil property research as well as limited integration of physics‐based vadose zone principles into the ML approaches. To facilitate this interdisciplinary research of ML in vadose zone characterization and processes, a paradigm of knowledge‐guided machine learning is suggested along with other data‐driven and ML model‐based research suggestions to advance future research. Core Ideas: Random forest and artificial neural network are two widely applied machine learning options for predicting vadose zone studies.A benchmark dataset is missing in soil property studies.We suggest vadose zone scientists explore more deep learning options and expand knowledge‐guided machine learning implementations. [ABSTRACT FROM AUTHOR]

This article addresses the class imbalance problem in urban gain modelling (UGM) of Tabriz and Isfahan megacities in Iran by proposing novel cost-sensitive machine learning models, namely costsensitive support vector machine (CSVM), random forest (CRF) and artificial neural network (CANN). Random sampling, a frequently utilized method, fails to effectively tackle this issue by biasing models towards no change samples, which outnumber change samples. The results showed that CRF exhibited the highest accuracy (AUC = 0.560), followed by CANN (AUC = 0.557) and CSVM (AUC = 0.448) in Isfahan. In Tabriz, CRF (AUC = 0.809) and CANN (AUC = 0.818) excelled, outperforming balanced sampling models constructed with ANN, RF and SVM with the AUROC of ANN and RF boosted by 15% and 2% in validation. By emphasizing the significance of addressing class imbalance appropriately, this research highlights the improvement in modelling outcomes achievable through the cost-sensitive models especially in Tabriz case. [ABSTRACT FROM AUTHOR]

Satellite‐based remote sensing missions have revolutionized our understanding of the Ocean state and dynamics. Among them, space‐borne altimetry provides valuable Sea Surface Height (SSH) measurements, used to estimate surface geostrophic currents. Due to the sensor technology employed, important gaps occur in SSH observations. Complete SSH maps are produced using linear Optimal Interpolations (OI) such as the widely used Data Unification and Altimeter Combination System (duacs). On the other hand, Sea Surface Temperature (SST) products have much higher data coverage and SST is physically linked to geostrophic currents through advection. We propose a new multi‐variate Observing System Simulation Experiment (OSSE) emulating 20 years of SSH and SST satellite observations. We train an Attention‐Based Encoder‐Decoder deep learning network (abed) on this data, comparing two settings: one with access to ground truth during training and one without. On our OSSE, we compare abed reconstructions when trained using either supervised or unsupervised loss functions, with or without SST information. We evaluate the SSH interpolations in terms of eddy detection. We also introduce a new way to transfer the learning from simulation to observations: supervised pre‐training on our OSSE followed by unsupervised fine‐tuning on satellite data. Based on real SSH observations from the Ocean Data Challenge 2021, we find that this learning strategy, combined with the use of SST, decreases the root mean squared error by 24% compared to OI. Plain Language Summary: The surface of the ocean is observed through various sensors embedded in satellites. Specifically, the height of the sea surface is a crucial variable as it can be used to estimate surface currents. It is currently measured through satellite altimeters, but the data acquisition process leaves gaps in their observations. Providing fully gridded maps of the sea surface height is thus an important interpolation problem. The widely used interpolated product has some troubles, especially when dealing with small and rapidly evolving eddies. To enhance its quality, we propose an artificial neural network, a trainable method able to estimate complete sea surface height images. The flexibility of these methods allows us to use different satellite information, such as the sea surface temperature, which has a better resolution. Usually, neural networks are trained on a data set upon which they learn the link between input and output data. However, in a realistic geoscience scenario, the output is never known for sure. We propose a data set that simulates this problem and explores methodologies to train these methods. Finally, we design a new way of learning SSH reconstruction using both simulated data and real satellite observation. Key Points: We developed a realistic simulation of satellite observations of sea surface height and temperatureWe compare deep learning supervised and unsupervised strategies to interpolate the sea surface heightWe present a hybrid learning strategy using supervised training on our simulated data and unsupervised fine‐tuning on real‐world data [ABSTRACT FROM AUTHOR]

Wildfires are uncontrolled fires fuelled by dry conditions, high winds, and flammable materials that profoundly impact vegetation, leading to significant consequences including noteworthy changes to ecosystems. In this study, we provide a novel methodology to understand and evaluate post-fire effects on vegetation. In regions affected by wildfires, earth-observation data from various satellite sources can be vital in monitoring vegetation and assessing its impact. These effects can be understood by detecting vegetation change over the years using a novel unsupervised method termed Deep Embedded Clustering (DEC), which enables us to classify regions based on whether there has been a change in vegetation after the fire. Our model achieves an impressive accuracy of 96.17%. Appropriate vegetation indices can be used to evaluate the evolution of vegetation patterns over the years; for this study, we utilized Enhanced Vegetation Index (EVI) based trend analysis showing the greening fraction, which ranges from 0.1 to 22.4 km2 while the browning fraction ranges from 0.1 to 18.1 km2 over the years. Vegetation recovery maps can be created to assess re-vegetation in regions affected by the fire, which is performed via a deep learning-based unsupervised method, Adaptive Generative Adversarial Neural Network Model (AdaptiGAN) on post-fire data collected from various regions affected by wildfire with a training error of 0.075 proving its capability. Based on the results obtained from the study, our approach tends to have notable merits when compared to pre-existing works. [ABSTRACT FROM AUTHOR]

This review focuses on the importance of identifying potential fishing zones in seawater for sustainable fishing practices. It explores features like sea surface temperature (SST) and sea surface height (SSH), along with classification methods such as classifiers. The features like SST, SSH, and different classifiers used to classify the data, have been figured out in this review study. This study underscores the importance of examining potential fishing zones using advanced analytical techniques. It thoroughly explores the methodologies employed by researchers, covering both past and current approaches. The examination centers on data characteristics and the application of classification algorithms for classification of potential fishing zones. Furthermore, the prediction of potential fishing zones relies significantly on the effectiveness of classification algorithms. Previous research has assessed the performance of models like support vector machines, naïve Bayes, and artificial neural networks (ANN). In the previous result, the results of support vector machine (SVM) were 97.6% more accurate than naive Bayes's 94.2% to classify test data for fisheries classification. By considering the recent works in this area, several recommendations for future works are presented to further improve the performance of the potential fishing zone models, which is important to the fisheries community. [ABSTRACT FROM AUTHOR]

The measurement of sea surface height (SSH), which is of great importance in the field of oceanography, can be obtained through the innovative technique of GNSS-R for remote sensing. This research utilizes the dataset from spaceborne GNSS-R platforms, the Cyclone Global Navigation Satellite System (CYGNSS) and FengYun-3E (FY-3E), as the primary source of data for retrieving sea surface height (SSH). The utilization of artificial neural networks (ANNs) allows for the accurate estimation of ocean surface height with a precision of meter-level accuracy throughout the period of 1–17 August 2022. As a traditional machine learning method, an ANN is employed to extract pertinent data features, facilitating the acquisition of precise sea surface height estimations. Additionally, separate models are devised for both GNSS-R platforms, one based on constant velocity (CV) and the other on constant acceleration (CA). The Interactive Multiple Model (IMM) is utilized as the main method to combine the four models and convert the likelihood of each model. The transition between the models allows the filters to effectively adapt to dynamic changes and complex environments. This approach relies on the fundamental notion of the Kalman filter (KF), which showcases robust noise handling capabilities in predicting the SSH, separately. The results demonstrate that the model interaction technology is capable of efficiently filtering and integrating SSH data, yielding a Root Mean Square Error (RMSE) of 1.03 m. This corresponds to a 9.84% enhancement compared to the retrieved height from CYGNSS and a 37.19% enhancement compared to the retrieved height from FY-3E. The model proposed in this paper provides a potential scheme for the GNSS-R data fusion of multiple platforms and multiple models. In the future, more data sources and more models can be added to achieve more accurate adaptive fusion. [ABSTRACT FROM AUTHOR]

An artificial neural network (ANN) algorithm, employing several Aqua MODerate-resolution Imaging Spectroradiometer (MODIS) channels, the retrieved cloud phase and total cloud visible optical depth, and temperature and humidity vertical profiles is trained to detect multilayer (ML) ice-over-water cloud systems identified by matched 2008 CloudSat and CALIPSO (CC) data. The trained multilayer cloud-detection ANN (MCANN) was applied to 2009 MODIS data resulting in combined ML and single layer detection accuracies of 87 % (89 %) and 86 % (89 %) for snow-free (snow-covered) regions during the day and night, respectively. Overall, it detects 55 % and ∼ 30 % of the CC ML clouds over snow-free and snow-covered surfaces, respectively, and has a relatively low false alarm rate. The net gain in accuracy, which is the difference between the true and false ML fractions, is 7.5 % and ∼ 2.0 % over snow-free and snow/ice-covered surfaces. Overall, the MCANN is more accurate than most currently available methods. When corrected for the viewing-zenith-angle dependence of each parameter, the ML fraction detected is relatively invariant across the swath. Compared to the CC ML variability, the MCANN is robust seasonally and interannually and produces similar distribution patterns over the globe, except in the polar regions. Additional research is needed to conclusively evaluate the viewing zenith angle (VZA) dependence and further improve the MCANN accuracy. This approach should greatly improve the monitoring of cloud vertical structure using operational passive sensors. [ABSTRACT FROM AUTHOR]

Global climate change has exacerbated alterations in urban thermal environments, significantly impacting the daily lives and health of city residents. Measuring and understanding urban land surface temperatures (LST) and their influencing factors is important in addressing global climate change and enhancing the well-being of residents. However, due to limitations in data precision and analytical methods, existing studies often overlook the microscale examination closely related to residents' daily lives, and lack a deep exploration of the spatial heterogeneity of the influencing factors. This leads to these results being ineffective in guiding the planning and construction of cities. Taking Shenzhen as a case study, our study investigates the effects of various microscale build environment characteristics of LST using street view images and machine learning. A convolutional neural network model adopting the SegNet architecture is used to perform semantic segmentation on street view images, extracting features of the microscale urban-built environment. The LST is inverted through the Google Earth Engine (GEE) platform. By using Multiscale Geographically Weighted Regression (MGWR) models, our study reveals the comprehensive impact of the urban-built environment on LST and its significant spatial heterogeneity. The findings indicate that the proportions of sky, roads, and buildings are positively correlated with LST, while trees have a significant cooling effect. Although earth and water can reduce LST, their overall contribution is minimal due to limitations in their area and distribution patterns. This study not only reveals the key factors affecting urban LST at the microscale but also emphasizes the necessity of considering the spatial heterogeneity of these factors' impacts. This suggests the need for targeted strategies for different areas to effectively improve the urban thermal environment and achieve sustainable urban development. [ABSTRACT FROM AUTHOR]

We present techniques for enhancing the look-up table (LUT) method, using the Second Simulation of a Satellite Signal in the Solar Spectrum Vector (6 SV) model for atmospheric correction (AC) and accurate surface reflectance (SR) computation across the multispectral (MS) KOMPSAT-3A channels. We improved the LUT-based SR accuracy using three interpolation and prediction methods for AC coefficients: minimum curvature surface (MCS), six-dimensional linear interpolation (6D), and a deep neural network (DNN). When assessed based on the solar zenith angle (SZA) and aerosol optical depth (AOD), MCS had limitations interpolating atmospheric effects, particularly at shorter wavelengths. The DNN method had high predictive ability for atmospheric effect variability with an increased SZA, but struggled to predict minor changes at low SZAs. In comparison, the 6D method, operating in real-time and considering all AC input variables, consistently retrieved high-quality SR across all MS channels. Our findings offer insights into each method's strengths and limitations, guiding future remote sensing research and applications. [ABSTRACT FROM AUTHOR]

Human LULCC is the many driver of environmental changes. Accurate and up-to-date current and predicted information on LULCC is important in land use planning and natural resource management; however, in Zambia, detailed information on LULCC is insufficient. Therefore, this study assessed the dynamics of LULC change (2000–2020) and future projections (2020–2030) for Zambia. The ESA CCI land cover maps, which have been developed from Sentinel-2 images were used in this study. This dataset has a grid spatial resolution of 300 m for the 2000, 2010 and 2020. The 31 ESA CCI Classification were reclassified into ten (10) local Classifications using the r.class module in QGIS 2.18.14. The 2000 and 2010 LULC maps were used to simulate the 2020 LULC scenario using Artificial Neural Network (Multi-layer Perception) algorithms in Modules for Land Use Change Evaluation (MOLUSCE) plugin in QGIS 2.18.14. The 2010 and 2020 maps were used to predict the 2030 LULC classes. The reference 2020 and predicted 2020 LULC maps were used to validate the model. Predicted against observed 2020 LULC map, Kappa (loc) statistic was 0.9869. The 2020 LULC patterns was successfully simulated using ANN-MLP with accuracy level of 95%. LULC classes were predicted for 2030 using the 2010–2020 calibration period. The predicted 2030 LULC types shows an increase in built-up (71.44%) and decrease in cropland (0.73%) with reference to 2020 LULC map. Dense forest (0.19%), grassland (0.85%) and bare land (1.37%) will reduce from 2020–2030. However, seasonally flooded, sparse forest, shrub land, wetland and water body will increase marginally. The largest LULC change is from forest into other LULC types. The insights from this study show that ANN-MLP can be used to predict LULCC, and that the generated information can be employed in land use planning and National Adaptation Plans at regional and national scale. [ABSTRACT FROM AUTHOR]

The High lAtitude sNow Detection and Estimation aLgorithm for ATMS (HANDEL-ATMS) is a new machine-learning (ML)-based snowfall retrieval algorithm for Advanced Technology Microwave Sounder (ATMS) observations that has been developed specifically to detect and quantify high-latitude snowfall events that often form in cold, dry environments and produce light snowfall rates. ATMS and the future European MetOp-SG Microwave Sounder offer good high-latitude coverage and sufficient microwave channel diversity (23 to 190 GHz), which allows surface radiometric properties to be dynamically characterized and the non-linear and sometimes subtle passive microwave response to falling snow to be detected. HANDEL-ATMS is based on a combined active–passive microwave observational dataset in the training phase, where each ATMS multichannel observation is associated with coincident (in time and space) CloudSat Cloud Profiling Radar (CPR) vertical snow profiles and surface snowfall rates. The main novelty of the approach is the radiometric characterization of the background surface (including snow-covered land and sea ice) at the time of the overpass to derive the multichannel surface emissivities and clear-sky contribution to be used in the snowfall retrieval process. The snowfall retrieval is based on four different artificial neural networks (ANNs) for snow water path (SWP) and surface snowfall rate (SSR) detection and estimate. HANDEL-ATMS shows very good detection capabilities, POD = 0.83, FAR = 0.18, and HSS = 0.68, for the SSR detection module. Estimation error statistics show a good agreement with CPR snowfall products for SSR >10-2 mm h -1 (RMSE = 0.08 mm h -1 , bias = 0.02 mm h -1). The analysis of the results for an independent CPR dataset and of selected snowfall events is evidence of the unique capability of HANDEL-ATMS to detect and estimate SWP and SSR also in the presence of extremely cold and dry environmental conditions typical of high latitudes. [ABSTRACT FROM AUTHOR]

Aerosol optical depth (AOD) constitutes a key parameter of aerosols, providing vital information for quantifying the aerosol burden and air quality at global and regional levels. This study demonstrates a machine learning strategy for retrieving AOD under cloud-free conditions based on the synergy of machine learning algorithms (MLAs) and ground-based solar irradiance data. The performance of the proposed methodology was investigated by applying different components of solar irradiance. In particular, the use of direct instead of global irradiance as a model feature led to better performance. The MLA-based AODs were compared to reference AERONET retrievals, which encompassed RMSE values between 0.01 and 0.15, regardless of the underlying climate and aerosol environments. Among the MLAs, artificial neural networks outperformed the other algorithms in terms of RMSE at 54% of the measurement sites. The overall performance of MLA-based AODs against AERONET revealed a high coefficient of determination (R2 = 0.97), MAE of 0.01, and RMSE of 0.02. Compared to satellite (MODIS) and reanalysis (MERRA-2 and CAMSRA) data, the MLA-AOD retrievals revealed the highest accuracy at all stations. The ML-AOD retrievals have the potential to expand and complement the AOD information in non-existing timeframes when solar irradiances are available. [ABSTRACT FROM AUTHOR]

Based on the data of the State of Global Air (2020), air quality deterioration in Thailand has caused ~32,000 premature deaths, while the World Health Organization evaluated that air pollutants can decrease the life expectancy in the country by two years. PM2.5 was collected at three air quality observatory sites in Chiang-Mai, Bangkok, and Phuket, Thailand, from July 2020 to June 2021. The concentrations of 25 elements (Na, Mg, Al, Si, S, Cl, K, Ca, Sc, Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn, Ga, As, Se, Br, Sr, Ba, and Pb) were quantitatively characterised using energy-dispersive X-ray fluorescence spectrometry. Potential adverse health impacts of some element exposures from inhaling PM2.5 were estimated by employing the hazard quotient and excess lifetime cancer risk. Higher cancer risks were detected in PM2.5 samples collected at the sampling site in Bangkok, indicating that vehicle exhaust adversely impacts human health. Principal component analysis suggests that traffic emissions, crustal inputs coupled with maritime aerosols, and construction dust were the three main potential sources of PM2.5. Artificial neural networks underlined agricultural waste burning and relative humidity as two major factors controlling the air quality of Thailand. [ABSTRACT FROM AUTHOR]

We explore to what extent data-driven prediction models have skills in forecasting daily sea-surface temperature (SST), which are comparable to or perform better than current physics-based operational systems over long-range forecast horizons. Three hybrid deep learning-based models are developed within the South China Sea (SCS) basin by integrating deep neural networks (back propagation, long short-term memory, and gated recurrent unit) with traditional empirical orthogonal function analysis and empirical mode decomposition. Utilizing a 40-year (1982–2021) satellite-based daily SST time series on a 0.25° grid, we train these models on the first 32 years (1982–2013) of detrended SST anomaly (SSTA) data. Their predictive accuracies are then validated using data from 2014 and tested over the subsequent seven years (2015–2021). The models' forecast skills are assessed using spatial anomaly correlation coefficient (ACC) and root-mean-square error (RMSE), with ACC proving to be a stricter metric. A forecast skill horizon, defined as the lead time before ACC drops below 0.6, is determined to be 50 days. The models are equally capable of achieving a basin-wide average ACC of ~0.62 and an RMSE of ~0.48 °C at this horizon, indicating a 36% improvement in RMSE over climatology. This implies that on average the forecast skill horizon for these models is beyond the available forecast length. Analysis of one model, the BP neural network, reveals a variable forecast skill horizon (5 to 50 days) for each individual day, showing that it can adapt to different time scales. This adaptability seems to be influenced by a number of mechanisms arising from the evident regional and global atmosphere–ocean coupling variations on time scales ranging from intraseasonal to decadal in the SSTA of the SCS basin. [ABSTRACT FROM AUTHOR]

Turbulent exchanges between sea ice and the atmosphere are known to influence the melting rate of sea ice, the development of atmospheric circulation anomalies and, potentially, teleconnections between polar and non-polar regions. Large model errors remain in the parametrization of turbulent heat fluxes over sea ice in climate models, resulting in significant uncertainties in projections of future climate. Fluxes are typically calculated using bulk formulae, based on Monin-Obukhov similarity theory, which have shown particular limitations in polar regions. Parametrizations developed specifically for polar conditions (e.g. representing form drag from ridges or melt ponds on sea ice) rely on sparse observations and thus may not be universally applicable. In this study, new data-driven parametrizations have been developed for surface turbulent fluxes of momentum, sensible heat and latent heat in the Arctic. Machine learning has already been used outside the polar regions to provide accurate and computationally inexpensive estimates of surface turbulent fluxes. To investigate the feasibility of this approach in the Arctic, we have fitted neural-network models to a reference dataset (SHEBA). Predictive performance has been tested using data from other observational campaigns. For momentum and sensible heat, performance of the neural networks is found to be comparable to, and in some cases substantially better than, that of a state-of-the-art bulk formulation. These results offer an efficient alternative to the traditional bulk approach in cases where the latter fails, and can serve to inform further physically based developments. [ABSTRACT FROM AUTHOR]

The article presents results of using remote sensing images and machine learning to map and assess land potential based on time-series of potential Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) composites. Land potential here refers to the potential vegetation productivity in the hypothetical absence of short-term anthropogenic influence, such as intensive agriculture and urbanization. Knowledge on this ecological land potential could support the assessment of levels of land degradation as well as restoration potentials. Monthly aggregated FAPAR time-series of three percentiles (0.05, 0.50 and 0.95 probability) at 250 m spatial resolution were derived from the 8-day GLASS FAPAR V6 product for 2000-2021 and used to determine long-term trends in FAPAR, as well as to model potential FAPAR in the absence of human pressure. CCa 3 million training points sampled from 12,500 locations across the globe were overlaid with 68 bio-physical variables representing climate, terrain, landform, and vegetation cover, as well as several variables representing human pressure including: population count, cropland intensity, nightlights and a human footprint index. The training points were used in an ensemble machine learning model that stacks three base learners (extremely randomized trees, gradient descended trees and artificial neural network) using a linear regressor as meta-learner. The potential FAPAR was then projected by removing the impact of urbanization and intensive agriculture in the covariate layers. The results of strict cross-validation show that the global distribution of FAPAR can be explained with an R2 of 0.89, with the most important covariates being growing season length, forest cover indicator and annual precipitation. From this model, a global map of potential monthly FAPAR for the recent year (2021) was produced, and used to predict gaps in actual vs. potential FAPAR. The produced global maps of actual vs. potential FAPAR and long-term trends were each spatially matched with stable and transitional land cover classes. The assessment showed large negative FAPAR gaps (actual lower than potential) for classes: urban, needle-leave deciduous trees, and flooded shrub or herbaceous cover, while strong negative FAPAR trends were found for classes: urban, sparse vegetation and rainfed cropland. On the other hand, classes: irrigated or post-flooded cropland, tree cover mixed leaf type, and broad-leave deciduous showed largely positive trends. The framework allows land managers to assess potential land degradation from two aspects: as an actual declining trend in observed FAPAR and as a difference between actual and potential vegetation FAPAR. [ABSTRACT FROM AUTHOR]

The presence of melt ponds on Arctic summer sea ice significantly alters its albedo and thereby the surface energy budget and mass balance. Large-scale observations of melt pond coverage and sea ice albedo are crucial to investigate the role of sea ice for Arctic amplification and its representation in global climate models. We present the new Melt Pond Detection 2 (MPD2) algorithm, which retrieves melt pond, sea ice, and open-ocean fractions as well as surface albedo from Sentinel-3 visible and near-infrared reflectances. In contrast to most other algorithms, our method uses neither fixed values for the spectral albedo of the surface constituents nor an artificial neural network. Instead, it aims for a fully physical representation of the reflective properties of the surface constituents based on their optical characteristics. The state vector X , containing the optical properties of melt ponds and sea ice along with the area fractions of melt ponds and open ocean, is optimized in an iterative procedure to match the measured reflectances and describe the surface state. A major problem in unmixing a compound pixel is that a mixture of half open water and half bright ice cannot be distinguished from a homogeneous pixel of darker ice. In order to overcome this, we suggest constraining the retrieval with a priori information. Initial values and constraint of the surface fractions are derived with an empirical retrieval which uses the same spectral reflectances as implemented in the physical retrieval. The snow grain size and optical thickness change with time, and thus the ice surface albedo changes throughout the season. Therefore, field observations of spectral albedo are used to develop a parameterization of the sea ice optical properties as a function of the temperature history of the sea ice. With these a priori data, the iterative optimization is initialized and constrained, resulting in a retrieval uncertainty of below 8 % for melt pond and 9 % for open-ocean fractions compared to the reference dataset. As reference data for evaluation, a 10 m resolution product of melt pond and open-ocean fraction from Sentinel-2 optical imagery is used. [ABSTRACT FROM AUTHOR]

In order to enhance the retrieval accuracy of cloud top height (CTH) from MODIS data, neural network models were employed based on Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) data. Three types of methods were established using MODIS inputs: cloud parameters, calibrated radiance, and a combination of both. From a statistical standpoint, models with combination inputs demonstrated the best performance, followed by models with calibrated radiance inputs, while models relying solely on calibrated radiance had poorer applicability. This work found that cloud top pressure (CTP) and cloud top temperature played a crucial role in CTH retrieval from MODIS data. However, within the same type of models, there were slight differences in the retrieved results, and these differences were not dependent on the quantity of input parameters. Therefore, the model with fewer inputs using cloud parameters and calibrated radiance was recommended and employed for individual case studies. This model produced results closest to the actual cloud top structure of the typhoon and exhibited similar cloud distribution patterns when compared with the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) CTHs from a climatic statistical perspective. This suggests that the recommended model has good applicability and credibility in CTH retrieval from MODIS images. This work provides a method to improve accurate CTHs from MODIS data for better utilization. [ABSTRACT FROM AUTHOR]

This study details a two-method, machine learning approach to predict current and short-term intensity change in global tropical cyclones (TCs), "D-MINT" and "D-PRINT." D-MINT and D-PRINT use infrared imagery and environmental scalar predictors, while D-MINT also employs microwave imagery. Results show that current TC intensity estimates from D-MINT and D-PRINT are more skillful than three established intensity estimation methods routinely used by operational forecasters for North Atlantic and eastern and western North Pacific TCs. Short-term intensity predictions are validated against five operational deterministic guidances at 6-, 12-, 18-, and 24-h lead times. D-MINT and D-PRINT are less skillful than NHC and consensus TC intensity predictions in North Atlantic and eastern North Pacific TCs, but are more skillful than the other guidances for at least half of the lead times. In western North Pacific, north Indian Ocean, and Southern Hemisphere TCs, D-MINT is more skillful than the JTWC and other individual TC intensity forecasts for over half of the lead times. When probabilistically predicting TC rapid intensification (RI), D-MINT is more skillful in North Atlantic and western North Pacific TCs than three operationally used RI guidances, but less skillful for yes–no RI forecasts. In addition, this work demonstrates the importance of microwave imagery, as D-MINT is more skillful than D-PRINT. Since D-MINT and D-PRINT are convolutional neural network models interrogating two-dimensional structures within TC satellite imagery, this study also demonstrates that those features can yield better short-term predictions than existing scalar statistics of satellite imagery in operational models. Finally, a diagnostics tool is revealed to aid the attribution of the D-MINT/D-PRINT intensity predictions. Significance Statement: This study develops a method to predict current and short-term forecasts of tropical cyclone (TC) intensity using artificial intelligence. The resultant models use a convolutional neural network (CNN) that can identify two-dimensional features in satellite imagery that are indicative of TC intensity and future intensity change. The performance results indicate that in several TC basins, the CNN approach is generally more skillful than alternative satellite-based estimates of TC intensity as well as operational short-term forecasts of deterministic intensity change and of similar skill to probabilistic rapid intensification forecasts. [ABSTRACT FROM AUTHOR]