Search

In the post-pandemic era, outdoor jogging has become an increasingly popular form of exercise due to the growing emphasis on health. It is essential to comprehensively analyze the factors influencing the spatial distribution of outdoor jogging activities and to propose planning strategies with practical guidance. Using multi-source geospatial big data and multiple models, this study constructs a comprehensive analytical framework to examine the association between environmental variables and the frequency of outdoor jogging activities in Guangzhou. Firstly, outdoor jogging trajectory data were collected from a fitness app, and potential influencing factors were selected based on multi-source big data from the perspectives of the built environment, street perception, and natural environment. For example, using the street-view imagery, objective environmental elements such as greenery and subjective elements such as safety perception were extracted from a human-centric perspective. Secondly, the framework included three models: a backward stepwise regression, an optimal parameters-based geographical detector, and a geographically weighted regression (GWR) model. These models served, to screen significant variables, identify the synergistic effects among the variables, and quantify the spatial heterogeneity of the effects, respectively. Finally, the study area was clustered based on the results of the GWR model to propose urban planning strategies with clear spatial positions and practical significance. The results indicated the following: (1) Factors related to the built environment and street perception significantly influence jogging frequency distribution. (2) Public sports facilities, the level of greenery, and safety perception were identified as key factors influencing jogging activities, representing the three aspects of service facilities, objective perception, and subjective perception, respectively. (3) Specifically, the influence of each factor on jogging activities displayed significant spatial variation. For instance, sports facilities and greenery level were positively correlated with jogging frequency in the city center. (4) Lastly, the study area was divided into four clusters, each representing different local associative characteristics between variables and jogging activities. The zonal planning recommendations have significant implications for urban planners and policymakers aiming to create jogging-friendly environments.

The Haiyang-2D (HY2D) satellite is the fourth ocean dynamics environment monitoring satellite launched by China. The satellite operates on a re-entry frozen orbit, which necessitates orbital maneuvers to maintain its designated path once the satellite’s sub-satellite point deviates beyond a certain threshold. However, the execution of orbit maneuvers presents a significant challenge to the field of Precise Orbit Determination (POD). The thesis selects the on-board GPS data of HY2D satellite in December 2023 and five maneuvering days of that year. Employing a multifaceted approach that includes the assessment of observational data quality, orbit overlap, external orbit validation, and SLR (Satellite Laser Ranging) verification, the research delves into precise orbit determination during both maneuver and non-maneuver periods. The results indicate that: (1) The average number of satellites tracked by the receiver is 6.4; (2) During the non-maneuver periods, the average RMS (Root Mean Square) value of the radial difference in the 6-h overlapping arc segment is 0.66 cm, and the three-dimensional position difference is about 1.16 cm; (3) When compared with the precision science orbits (PSO) provided by CNES (Centre National d’Études Spatiales), the average values of the RMS values of the differences in the radial (R), transverse (T), and normal (N) directions during the non-maneuver and maneuver periods are respectively 1.32 cm, 2.31 cm, 1.92 cm and 3.04 cm, 8.78 cm, 2.72 cm. (4) The SLR verification of the orbit revealed a residual RMS of 2.24 cm. This suggests that by incorporating the modeling of maneuver forces during the maneuver periods, the impact of orbital maneuvers on orbit determination can be mitigated.

In the original publication [...]

Precise delineation of marine aquaculture areas is vital for the monitoring and protection of marine resources. However, due to the coexistence of diverse marine aquaculture areas and complex marine environments, it is still difficult to accurately delineate mariculture areas from very high spatial resolution (VHSR) images. To solve such a problem, we built a novel Transformer–CNN hybrid Network, named TCNet, which combined the advantages of CNN for modeling local features and Transformer for capturing long-range dependencies. Specifically, the proposed TCNet first employed a CNN-based encoder to extract high-dimensional feature maps from input images. Then, a hierarchical lightweight Transformer module was proposed to extract the global semantic information. Finally, it employed a coarser-to-finer strategy to progressively recover and refine the classification results. The results demonstrate the effectiveness of TCNet in accurately delineating different types of mariculture areas, with an IoU value of 90.9%. Compared with other state-of-the-art CNN or Transformer-based methods, TCNet showed significant improvement both visually and quantitatively. Our methods make a significant contribution to the development of precision agricultural in coastal regions.

Accurate precipitation forecasting plays an important role in disaster prevention and mitigation. Currently, precipitation forecasting mainly depends on numerical weather prediction and radar observation. However, ground-based radar observation has limited coverage and is easily influenced by the environment, resulting in the limited coverage of precipitation forecasts. The infrared observations of geosynchronous earth orbit (GEO) satellites have been widely used in precipitation estimation due to their extensive coverage, continuous monitoring, and independence from environmental influences. In this study, we propose a multi-channel satellite precipitation forecasting network (MCSPF-Net) based on 3D convolutional neural networks. The network uses real-time multi-channel satellite observations as input to forecast precipitation for the future 4 h (30-min intervals), utilizing the observation characteristics of GEO satellites for wide coverage precipitation forecasting. The experimental results showed that the precipitation forecasting results of MCSPF-Net have a high correlation with the Global Precipitation Measurement product. When evaluated using rain gauges, the forecasting results of MCSPF-Net exhibited higher critical success index (0.25 vs. 0.21) and correlation coefficients (0.33 vs. 0.23) and a lower mean square error (0.36 vs. 0.93) compared to the numerical weather prediction model. Therefore, the multi-channel satellite observation-driven MCSPF-Net proves to be an effective approach for predicting near future precipitation.

Determining residue cover on agricultural land is an important task. Residue cover helps reduce soil erosion and helps sequester carbon. Many studies have used either spectral indices or classification techniques to map residue cover using satellite imagery. Unfortunately, most of these studies use only a few spectral indices or classification techniques and generally only study an area for a single year with a certain level of success. This manuscript presents an investigation of five spectral indices and six classification techniques over four years to determine if a single spectral index or classification technique performs consistently better than the others. A second objective is to determine whether using the coefficient of determination (R2) from the relationship between residue cover and a spectral index is a reasonable substitute for calculating accuracy. Field visits were conducted for each of the years studied and used to create the correlations with the spectral indices and as ground truth for the classification techniques. It was found that no spectral index/classification technique is consistently better than all the others. Classification techniques tended to be more accurate in 2011 and 2013, while spectral indices tended to be more accurate in 2015 and 2018. The combination of spectral indices/classification techniques outperformed the individual approach. For the second objective, it was found that R2 is not a great indicator of accuracy. Root mean square error (RMSE) is a better indicator of accuracy than R2. However, simply calculating the accuracy would be the best of all.

In recent years, there have been many multimodal works in the field of remote sensing, and most of them have achieved good results in the task of land-cover classification. However, multi-scale information is seldom considered in the multi-modal fusion process. Secondly, the multimodal fusion task rarely considers the application of attention mechanism, resulting in a weak representation of the fused feature. In order to better use the multimodal data and reduce the losses caused by the fusion of different modalities, we proposed a TRMSF (Transformer and Multi-scale fusion) network for land-cover classification based on HSI (hyperspectral images) and LiDAR (Light Detection and Ranging) images joint classification. The network enhances multimodal information fusion ability by the method of attention mechanism from Transformer and enhancement using multi-scale information to fuse features from different modal structures. The network consists of three parts: multi-scale attention enhancement module (MSAE), multimodality fusion module (MMF) and multi-output module (MOM). MSAE enhances the ability of feature representation from extracting different multi-scale features of HSI, which are used to fuse with LiDAR feature, respectively. MMF integrates the data of different modalities through attention mechanism, thereby reducing the loss caused by the data fusion of different modal structures. MOM optimizes the network by controlling different outputs and enhances the stability of the results. The experimental results show that the proposed network is effective in multimodality joint classification.

Evapotranspiration (ET) is a crucial part of commercial grapevine production in California, and the partitioning of this quantity allows the separate assessment of soil and vine water and energy fluxes. This partitioning has an important role in agriculture since it is related to grapevine stress, yield quality, irrigation efficiency, and growth. Satellite remote sensing-based methods provide an opportunity for ET partitioning at a subfield scale. However, medium-resolution satellite imagery from platforms such as Landsat is often insufficient for precision agricultural management at the plant scale. Small, unmanned aerial systems (sUAS) such as the AggieAir platform from Utah State University enable ET estimation and its partitioning over vineyards via the two-source energy balance (TSEB) model. This study explores the assessment of ET and ET partitioning (i.e., soil water evaporation and plant transpiration), considering three different resistance models using ground-based information and aerial high-resolution imagery from the Grape Remote sensing Atmospheric Profile and Evapotranspiration eXperiment (GRAPEX). We developed a new method for temperature partitioning that incorporated a quantile technique separation (QTS) and high-resolution sUAS information. This new method, coupled with the TSEB model (called TSEB-2TQ), improved sensible heat flux (H) estimation, regarding the bias, with around 61% and 35% compared with the H from the TSEB-PT and TSEB-2T, respectively. Comparisons among ET partitioning estimates from three different methods (Modified Relaxed Eddy Accumulation—MREA; Flux Variance Similarity—FVS; and Conditional Eddy Covariance—CEC) based on EC flux tower data show that the transpiration estimates obtained from the FVS method are statistically different from the estimates from the MREA and the CEC methods, but the transpiration from the MREA and CEC methods are statistically the same. By using the transpiration from the CEC method to compare with the transpiration modeled by different TSEB models, the TSEB-2TQ shows better agreement with the transpiration obtained via the CEC method. Additionally, the transpiration estimation from TSEB-2TQ coupled with different resistance models resulted in insignificant differences. This comparison is one of the first for evaluating ET partitioning estimation from sUAS imagery based on eddy covariance-based partitioning methods.

Accurate characterization of evapotranspiration (ET) is imperative in water-limited cropping systems such as California vineyards and almond orchards. Satellite-based ET modeling techniques, including the atmosphere–land exchange inverse model (ALEXI) and associated flux disaggregation technique (DisALEXI), have proven reliable in determining field scale ET. However, validation efforts typically focus on ET and omit an evaluation of partitioned evaporation (E) and transpiration (T). ALEXI/DisALEXI is based on the two-source energy balance (TSEB) model, making it uniquely qualified to derive E and T individually. The current study evaluated E and T estimates derived using two formulations of DisALEXI; one based on Priestley-Taylor (DisALEXI-PT) and the other on Penman-Monteith (DisALEXI-PM). The modeled values were validated against partitioned fluxes derived from the conditional eddy covariance (CEC) approach using EC flux towers in three wine grape vineyards and three almond orchards for the year 2021. Modeled estimates were derived using Landsat 8 Collection 2 thermal infrared and surface reflectance imagery as well as Harmonized Landsat and Sentinel-2 surface reflectance datasets as input into DisALEXI. The results indicated that the modeled total ET fluxes were similar between the two methods, but the partitioned values diverged, with DisALEXI-PT overestimating E and slightly underestimating T when compared to CEC estimates. Conversely, DisALEXI-PM agreed better with CEC-derived E and overestimated T estimates under non-advective conditions. Compared to one another, DisALEXI-PM estimated canopy temperatures ~5 °C cooler and soil temperatures ~5 °C warmer than DisALEXI-PT, causing differences in E and T of −2.6 mm day−1 and +2.6 mm day−1, respectively. The evaluation of the iterative process required for DisALEXI indicates DisALEXI-PM ET values converge on ALEXI ET with proportionate adjustments to E and T, while DisALEXI-PT convergence is driven by adjustments to E. The analysis presented here can potentially drive improvements in the modeling framework to provide specific soil and canopy consumptive water use information in unique canopy structures, allowing for improved irrigation and water use efficiencies in these water-limited systems.

Convolution-based recurrent neural networks and convolutional neural networks have been used extensively in spatiotemporal prediction. However, these methods tend to concentrate on fixed-scale spatiotemporal state transitions and disregard the complexity of spatiotemporal motion. Through statistical analysis, we found that the distribution of the spatiotemporal sequence and the variety of spatiotemporal motion state transitions exhibit some regularity. In light of these statistics and observations, we propose the Multi-scale Spatiotemporal Neural Network (MSSTNet), an end-to-end neural network based on 3D convolution. It can be separated into three major child modules: a distribution feature extraction module, a multi-scale motion state capture module, and a feature decoding module. Furthermore, the MSST unit is designed to model multi-scale spatial and temporal information in the multi-scale motion state capture module. We first conduct the experiments on the MovingMNIST dataset, which is the most commonly used dataset in the field of spatiotemporal prediction, MSSTNet can achieve state-of-the-art results for this dataset, and ablation experiments demonstrate that the MSST unit has positive significance for spatiotemporal prediction. In addition, this paper applies the model to valuable precipitation nowcasting, due to efficiently capturing the multi-scale information of distribution and motion, the new MSSTNet model can predict the real-world radar echo more accurately.

The study of cloud types is critical for understanding atmospheric motions and climate predictions; for example, accurately classified cloud products help improve meteorological predicting accuracies. However, the current satellite cloud classification methods generally analyze the threshold change in a single pixel and do not consider the relationship between the surrounding pixels. The classification development relies heavily on human recourses and does not fully utilize the data-driven advantages of computer models. Here, a new intelligent cloud classification method based on the U-Net network (CLP-CNN) is developed to obtain more accurate, higher frequency, and larger coverage cloud classification products. The experimental results show that the CLP-CNN network can complete a cloud classification task of 800 × 800 pixels in 0.9 s. The classification area covers most of China, and the classification task only needs to use the original L1-level data, which can meet the requirements of a real-time operation. With the Himawari-8 CLTYPE product and the CloudSat 2B-CLDCLASS product as the test comparison target, the CLP-CNN network results matched the Himawari-8 product highly by 76.8%. The probability of detection (POD) was greater than 0.709 for clear skies, deep-convection, and Cirrus–Stratus-type clouds. The probability of detection (POD) and accuracy are improved compared with other deep learning methods.

Remote sensing image (RSI) scene classification aims to identify the semantic categories of remote sensing images based on their contents. Owing to the strong learning capability of deep convolutional neural networks (CNNs), RSI scene classification methods based on CNNs have drawn much attention and achieved remarkable performance. However, such outstanding deep neural networks are usually computationally expensive and time-consuming, making them impossible to apply on resource-constrained edge devices, such as the embedded systems used on drones. To tackle this problem, we introduce a novel pair-wise similarity knowledge distillation method, which could reduce the model complexity while maintaining satisfactory accuracy, to obtain a compact and efficient deep neural network for RSI scene classification. Different from the existing knowledge distillation methods, we design a novel distillation loss to transfer the valuable discriminative information, which could reduce the within-class variations and restrain the between-class similarity, from the cumbersome model to the compact model. This method could obtain the compact student model with higher performance compared with existing knowledge distillation methods in RSI scene classification. To be specific, we distill the probability outputs between sample pairs with the same label and match the probability outputs between the teacher and student models. Experiments on three public benchmark datasets for RSI scene classification, i.e., AID, UCMerced, and NWPU-RESISC datasets, verify that the proposed method could effectively distill the knowledge and result in a higher performance.

Evapotranspiration (ET) represents crop water use and is a key indicator of crop health. Accurate estimation of ET is critical for agricultural irrigation and water resource management. ET retrieval using energy balance methods with remotely sensed thermal infrared data as the key input has been widely applied for irrigation scheduling, yield prediction, drought monitoring and so on. However, limitations on the spatial and temporal resolution of available thermal satellite data combined with the effects of cloud contamination constrain the amount of detail that a single satellite can provide. Fusing satellite data from different satellites with varying spatial and temporal resolutions can provide a more continuous estimation of daily ET at field scale. In this study, we applied an ET fusion modeling system, which uses a surface energy balance model to retrieve ET using both Landsat and Moderate Resolution Imaging Spectroradiometer (MODIS) data and then fuses the Landsat and MODIS ET retrieval timeseries using the Spatial-Temporal Adaptive Reflectance Fusion Model (STARFM). In this paper, we compared different STARFM ET fusion implementation strategies over various crop lands in the central California. In particular, the use of single versus two Landsat-MODIS pair images to constrain the fusion is explored in cases of rapidly changing crop conditions, as in frequently harvested alfalfa fields, as well as an improved dual-pair method. The daily 30 m ET retrievals are evaluated with flux tower observations and analyzed based on land cover type. This study demonstrates improvement using the new dual-pair STARFM method compared with the standard one-pair STARFM method in estimating daily field scale ET for all the major crop types in the study area.

For ships on voyage, using satellite remote sensing observations is an effective way to access ocean temperature. However, satellite remote sensing observations can only provide the surface information. Additionally, this information obtained from satellite remote sensing observations is delayed data. Although some previous studies have investigated the spatial inversion (spatial extension) or temporal prediction (temporal extension) of satellite remote sensing observations, these studies did not integrate ship survey observations and the temporal prediction is limited to sea surface temperature (SST). To address these issues, we propose an information spatial-temporal extension (ISTE) algorithm for remote sensing SST. Based on deep neural networks (DNNs), the ISTE algorithm can effectively fuse the satellite remote sensing SST data, ship survey observations data, and historical data to generate a four-dimensional (4D) temperature prediction field. Experimental results show that the ISTE algorithm performs superior prediction accuracy relative to linear regression analysis-based prediction. The prediction results of ISTE exhibit high coefficient of determination (0.9936) and low root mean squared errors (around 0.7 °C) compared with Argo observation data. Therefore, for shipborne predictions, the ISTE algorithm driven by satellite remote sensing SST can be as an effective approach to predict ocean temperature.

Crop emergence is a critical stage for crop development modeling, crop condition monitoring, and biomass accumulation estimation. Green-up dates (or the start of the season) detected from remote sensing time series are related to, but generally lag, crop emergence dates. In this paper, we refine the within-season emergence (WISE) algorithm and extend application to five Corn Belt states (Iowa, Illinois, Indiana, Minnesota, and Nebraska) using routine harmonized Landsat and Sentinel-2 (HLS) data from 2018 to 2020. Green-up dates detected from the HLS time series were assessed using field observations and near-surface measurements from PhenoCams. Statistical descriptions of green-up dates for corn and soybeans were generated and compared to county-level planting dates and district- to state-level crop emergence dates reported by the National Agricultural Statistics Service (NASS). Results show that emergence dates for corn and soybean can be reliably detected within the season using the HLS time series acquired during the early growing season. Compared to observed crop emergence dates, green-up dates from HLS using WISE were ~3 days later at the field scale (30-m). The mean absolute difference (MAD) was ~7 days and the root mean square error (RMSE) was ~9 days. At the state level, the mean differences between median HLS green-up date and median crop emergence date were within 2 days for 2018–2020. At this scale, MAD was within 4 days, and RMSE was less than 5 days for both corn and soybeans. The R-squares were 0.73 and 0.87 for corn and soybean, respectively. The 2019 late emergence of crops in Corn Belt states (1–4 weeks to five-year average) was captured by HLS green-up date retrievals. This study demonstrates that routine within-season mapping of crop emergence/green-up at the field scale is practicable over large regions using operational satellite data. The green-up map derived from HLS during the growing season provides valuable information on spatial and temporal variability in crop emergence that can be used for crop monitoring and refining agricultural statistics used in broad-scale modeling efforts.

Mediterranean oak savanna is composed of a mixture of scattered oak trees, crops, pasture, and shrubs. It is the most widespread agroforestry landscape in Europe, and its conservation faces multiple threats including water scarcity, which has been exacerbated by global warming and greater climate variability. Evapotranspiration (ET) can be used as a proxy of the vegetation water status and response to water shortage conditions, providing relevant information about the ecosystem stability and its hydrological dynamics. This study evaluates a framework to estimate ET at multiple spatial and temporal scales and applies it to the monitoring of the oak savanna vegetation water consumption for the years 2013–2015. We used a remote sensing-based energy balance model (ALEXI/DisALEXI approach), and the STARFM data fusion technique to provide daily ET estimates at 30 m resolution. The results showed that modeled energy balance components compared well to ground measurements collected by an eddy covariance system, with root mean square error (RMSE) values ranging between 0.60 and 2.18 MJ m−2 d−1, depending on the sensor dataset (MODIS or Landsat) and the flux. The daily 30 m ET series generated by STARFM presented an RMSE value of 0.67 mm d−1, which yielded a slight improvement compared to using MODIS resolution or more simple interpolation approaches with Landsat. However, the major advantage of the high spatio-temporal resolution was found in the analysis of ET dynamics over different vegetation patches that shape the landscape structure and create different microclimates. Fine-scale ET maps (30 m, daily) provide key information difficult to detect at a coarser spatial resolution over heterogeneous landscapes and may assist management decisions at the field and farm scale.

A new approach is proposed to derive evapotranspiration (E) and irrigation requirements by implementing the combination equation models of Penman–Monteith and Shuttleworth and Wallace with surface parameters and resistances derived from Sentinel-2 data. Surface parameters are derived from Sentinel-2 and used as an input in these models; namely: the hemispherical shortwave albedo, leaf area index and water status of the soil and canopy ensemble evaluated by using a shortwave infrared-based index. The proposed approach has been validated with data acquired during the GRAPEX (Grape Remote-sensing Atmospheric Profile and Evapotranspiration eXperiment) in California irrigated vineyards. The E products obtained with the combination equation models are evaluated by using eddy covariance flux tower measurements and are additionally compared with surface energy balance models with Landsat-7 and -8 thermal infrared data. The Shuttleworth and Wallace (S-W S-2) model provides an accuracy comparable to thermal-based methods when using local meteorological data, with daily E errors < 1 mm/day, which increased from 1 to 1.5 mm/day using meteorological forcing data from atmospheric models. The advantage of using the S-W S-2 modeling approach for monitoring ET is the high temporal revisit time of the Sentinel-2 satellites and the finer pixel resolution. These results suggest that, by integrating the thermal-based data fusion approach with the S-W S-2 modeling scheme, there is the potential to increase the frequency and reliability of satellite-based daily evapotranspiration products.

Accurate and frequent monitoring of evapotranspiration (ET) at sub-field scales can provide valuable information for agricultural water management, quantifying crop water use and stress toward the goal of increasing crop water use efficiency and production. Using land-surface temperature (LST) data retrieved from Landsat thermal infrared (TIR) imagery, along with surface reflectance data describing albedo and vegetation cover fraction, surface energy balance models can generate ET maps down to a 30 m spatial resolution. However, the temporal sampling by such maps can be limited by the relatively infrequent revisit period of Landsat data (8 days for combined Landsats 7 and 8), especially in cloudy areas experiencing rapid changes in moisture status. The Sentinel-2 (S2) satellites, as a good complement to the Landsat system, provide surface reflectance data at 10–20 m spatial resolution and 5 day revisit period but do not have a thermal sensor. On the other hand, the Visible Infrared Imaging Radiometer Suite (VIIRS) provides TIR data on a near-daily basis with 375 m resolution, which can be refined through thermal sharpening using S2 reflectances. This study assesses the utility of augmenting the Harmonized Landsat and Sentinel-2 (HLS) dataset with S2-sharpened VIIRS as a thermal proxy source on S2 overpass days, enabling 30 m ET mapping at a potential combined frequency of 2–3 days (including Landsat). The value added by including VIIRS-S2 is assessed both retrospectively and operationally in comparison with flux tower observations collected from several U.S. agricultural sites covering a range of crop types. In particular, we evaluate the performance of VIIRS-S2 ET estimates as a function of VIIRS view angle and cloud masking approach. VIIRS-S2 ET retrievals (MAE of 0.49 mm d−1 against observations) generally show comparable accuracy to Landsat ET (0.45 mm d−1) on days of commensurate overpass, but with decreasing performance at large VIIRS view angles. Low-quality VIIRS-S2 ET retrievals linked to imperfect VIIRS/S2 cloud masking are also discussed, and caution is required when applying such data for generating ET timeseries. Fused daily ET time series benefited during the peak growing season from the improved multi-source temporal sampling afforded by VIIRS-S2, particularly in cloudy regions and over surfaces with rapidly changing vegetation conditions, and value added for real-time monitoring applications is discussed. This work demonstrates the utility and feasibility of augmenting the HLS dataset with sharpened VIIRS TIR imagery on S2 overpass dates for generating high spatiotemporal resolution ET products.

Cover crops are planted during the off-season to protect the soil and improve watershed management. The ability to map cover crop termination dates over agricultural landscapes is essential for quantifying conservation practice implementation, and enabling estimation of biomass accumulation during the active cover period. Remote sensing detection of end-of-season (termination) for cover crops has been limited by the lack of high spatial and temporal resolution observations and methods. In this paper, a new within-season termination (WIST) algorithm was developed to map cover crop termination dates using the Vegetation and Environment monitoring New Micro Satellite (VENµS) imagery (5 m, 2 days revisit). The WIST algorithm first detects the downward trend (senescent period) in the Normalized Difference Vegetation Index (NDVI) time-series and then refines the estimate to the two dates with the most rapid rate of decrease in NDVI during the senescent period. The WIST algorithm was assessed using farm operation records for experimental fields at the Beltsville Agricultural Research Center (BARC). The crop termination dates extracted from VENµS and Sentinel-2 time-series in 2019 and 2020 were compared to the recorded termination operation dates. The results show that the termination dates detected from the VENµS time-series (aggregated to 10 m) agree with the recorded harvest dates with a mean absolute difference of 2 days and uncertainty of 4 days. The operational Sentinel-2 time-series (10 m, 4–5 days revisit) also detected termination dates at BARC but had 7% missing and 10% false detections due to less frequent temporal observations. Near-real-time simulation using the VENµS time-series shows that the average lag times of termination detection are about 4 days for VENµS and 8 days for Sentinel-2, not including satellite data latency. The study demonstrates the potential for operational mapping of cover crop termination using high temporal and spatial resolution remote sensing data.

Leaf area index (LAI) is an essential indicator of crop development and growth. For many agricultural applications, satellite-based LAI estimates at the farm-level often require near-daily imagery at medium to high spatial resolution. The combination of data from different ongoing satellite missions, Sentinel 2 (ESA) and Landsat 8 (NASA), provides this opportunity. In this study, we evaluated the leaf area index generated from three methods, namely, existing vegetation index (VI) relationships applied to Harmonized Landsat-8 and Sentinel-2 (HLS) surface reflectance produced by NASA, the SNAP biophysical model, and the THEIA L2A surface reflectance products from Sentinel-2. The intercomparison was conducted over the agricultural scheme in Bekaa (Lebanon) using a large set of in-field LAIs and other biophysical measurements collected in a wide variety of canopy structures during the 2018 and 2019 growing seasons. The major studied crops include herbs (e.g., cannabis: Cannabis sativa, mint: Mentha, and others), potato (Solanum tuberosum), and vegetables (e.g., bean: Phaseolus vulgaris, cabbage: Brassica oleracea, carrot: Daucus carota subsp. sativus, and others). Additionally, crop-specific height and above-ground biomass relationships with LAIs were investigated. Results show that of the empirical VI relationships tested, the EVI2-based HLS models statistically performed the best, specifically, the LAI models originally developed for wheat (RMSE:1.27), maize (RMSE:1.34), and row crops (RMSE:1.38). LAI derived through European Space Agency’s (ESA) Sentinel Application Platform (SNAP) biophysical processor underestimated LAI and provided less accurate estimates (RMSE of 1.72). Additionally, the S2 SeLI LAI algorithm (from SNAP biophysical processor) produced an acceptable accuracy level compared to HLS-EVI2 models (RMSE of 1.38) but with significant underestimation at high LAI values. Our findings show that the LAI-VI relationship, in general, is crop-specific with both linear and non-linear regression forms. Among the examined indices, EVI2 outperformed other vegetation indices when all crops were combined, and therefore it can be identified as an index that is best suited for a unified algorithm for crops in semi-arid irrigated regions with heterogeneous landscapes. Furthermore, our analysis shows that the observed height-LAI relationship is crop-specific and essentially linear with an R2 value of 0.82 for potato, 0.79 for wheat, and 0.50 for both cannabis and tobacco. The ability of the linear regression to estimate the fresh and dry above-ground biomass of potato from both observed height and LAI was reasonable, yielding R2: ~0.60.

A well-planned irrigation management strategy is crucial for successful wine grape production and is highly dependent on accurate assessments of water stress. Precision irrigation practices may benefit from the quantification of within-field spatial variability and temporal patterns of evapotranspiration (ET). A spatiotemporal modeling framework is proposed to delineate the vineyard into homogeneous areas (i.e., management zones) according to their ET patterns. The dataset for this study relied on ET retrievals from multiple satellite platforms, generating estimates at high spatial (30 m) and temporal (daily) resolutions for a Vitis vinifera Pinot noir vineyard in the Central Valley of California during the growing seasons of 2015-2018. Time-series decomposition was used to deconstruct the time series of each pixel into three components: long-term trend, seasonality, and remainder, which indicates daily fluctuations. For each time-series component, a time-series clustering (TSC) algorithm was applied to partition the time series of all pixels into homogeneous groups and generate TSC maps. The TSC maps were compared for spatial similarities using the V-measure statistic. A random forest (RF) classification algorithm was used for each TSC map against six environmental variables (elevation, slope, northness, lithology, topographic wetness index, and soil type) to check for spatial association between ET-TSC maps and the local characteristics in the vineyard. Finally, the TSC maps were used as independent variables against yield (ton ha-1) using analysis of variance (ANOVA) to assess whether the TSC maps explained yield variability. The trend and seasonality TSC maps had a moderate spatial association (V = 0.49), while the remainder showed dissimilar spatial patterns to seasonality and trend. The RF model showed high error matrix-based prediction accuracy levels ranging between 86% and 90%. For the trend and seasonality models, the most important predictor was soil type, followed by elevation, while the remainder TSC was strongly linked with northness spatial variability. The yield levels corresponding to the two clusters in all TSC were significantly different. These findings enabled spatial quantification of ET time series at different temporal scales that may benefit within-season decision-making regarding the amounts, timing, intervals, and location of irrigation. The proposed framework may be applicable to other cases in both agricultural systems and environmental modeling.

Remotely sensed data have been used in crop condition monitoring for decades. Traditionally, crop growth conditions were assessed by comparing Normalized Difference Vegetation Index (NDVI) of the current year and past years at a pixel scale on the same calendar day. The assumption of this comparison is that the different years’ crops were at the same growing stage on the same day. However, this assumption is often violated in reality. This paper proposes to combine remotely sensed data and meteorological data to assess corn growth conditions at the same growth stages at county level. The proposed approach uses the active accumulated temperature (AAT) computed from Daymet, a daily weather data product, to align different years of NDVI time series at the same growth stages estimated from AATs. The study area covers Carroll County, Iowa. The best index slope extraction (BISE) method and Savitzky−Golay filter are used to filter noise and to reconstruct 11 years of corn growing season NDVI time series from 250 m MODIS daily surface reflectance data product (MOD09GQ). The corn growth stages are identified every year with precise Julian dates from AAT time series. The corn growth conditions are assessed based on the aligned growth stages. The validation of the assessed crop conditions is performed based on National Agricultural Statistics Service (NASS) reports. The study indicates that the crop condition assessment results based on aligned growth stages are consistent with the NASS reported results and they are more reliable than the results based on the same calendar days. The proposed method provides not only crop growth condition information but also crop phenology information. Potentially, it can help improve crop yield prediction since it can effectively measure crop growth changes with NDVI and AAT data.

In viticulture, deficit irrigation strategies are often implemented to control vine canopy growth and to impose stress at critical stages of vine growth to improve wine grape quality. To support deficit irrigation scheduling, remote sensing technologies can be employed in the mapping of evapotranspiration (ET) at the field to sub-field scales, quantifying time-varying vineyard water requirements and actual water use. In the current study, we investigate the utility of ET maps derived from thermal infrared satellite imagery over a vineyard in the Central Valley of California equipped with a variable rate drip irrigation (VRDI) system which enables differential water applications at the 30 × 30 m scale. To support irrigation management at that scale, we utilized a thermal-based multi-sensor data fusion approach to generate weekly total actual ET (ETa) estimates at 30 m spatial resolution, coinciding with the resolution of the Landsat reflectance bands. Crop water requirements (ETc) were defined with a vegetative index (VI)-based approach. To test capacity to capture stress signals, the vineyard was sub-divided into four blocks with different irrigation management strategies and goals, inducing varying degrees of stress during the growing season. Results indicate derived weekly total ET from the thermal-based data fusion approach match well with observations. The thermal-based method was also able to capture the spatial heterogeneity in ET over the vineyard due to a water stress event imposed on two of the four vineyard blocks. This transient stress event was not reflected in the VI-based ETc estimate, highlighting the value of thermal band imaging. While the data fusion system provided valuable information, latency in current satellite data availability, particularly from Landsat, impacts operational applications over the course of a growing season.

Due to the fact that WorldView-2 (WV2) has a small time lag while acquiring images from panchromatic (PAN) and two multispectral (MS1 and MS2) sensors, a moving vehicle is located at different positions in three image bands. Consequently, such displacement can be utilized to identify moving vehicles, and vehicle information, such as speed and direction can be estimated. In this paper, we focus on moving vehicle detection according to the displacement information and present a novel processing chain. The vehicle locations are extracted by an improved morphological detector based on the vehicle’s shape properties. To make better use of the time lag between MS1 and MS2, a band selection process is performed by both visual inspection and quantitative analysis. Moreover, three spectral-neighbor band pairs, which have a major contribution to vehicle identification, are selected. In addition, we improve the spatial and spectral analysis method by incorporating local ERGAS index analysis (ERGAS-SNS) to identify moving vehicles. The experimental results on WV2 images showed that the correctness, completeness and quality rates of the proposed method were about 94%, 91% and 86%, respectively. Thus, the proposed method has good performance for moving vehicle detection and information extraction.

Surface bare soil albedo is an important variable in climate modeling studies and satellite-based retrievals of land-surface properties. In this study, we used multiyear 500 m albedo products from the Moderate Resolution Imaging Spectroradiometer (MODIS) to derive the bare soil albedo for seven spectral bands and three broadbands over the contiguous United States (CONUS). The soil line based on red and green spectral signatures derived from MODIS data was used as the basis to detect and extract bare soil albedo. A comparison against bare soil albedo derived from 30 m Landsat data has been made, showing that the MODIS bare soil albedo had a bias of 0.003 and a root-mean-square-error (RMSE) of 0.036. We found that the bare soil albedo was negatively correlated with soil moisture from the Advanced Microwave Scanning Radiometer-Earth Observing System (AMSR-E), with a relatively stable exponential relationship reflecting the darkening effect that moisture has on most soils. However, quantification of the relationship between bare soil albedo and soil moisture still needs to be improved through simultaneous and instantaneous measurements at a finer spatial resolution. Statistics of the multiyear climatological bare soil albedos calculated using soil types and the International Geosphere-Biosphere Programme (IGBP) land cover types suggest that: Land cover type is a better indicator for determining the magnitude of bare soil albedos for the vegetated areas, as the vegetation density is correlated with soil moisture; and soil type is a better indicator for determining the slope of soil lines over sparsely vegetated areas, as it contains information of the soil texture, roughness, and composition. The generated bare soil albedo can be applied to improve the parameterization of surface energy budget in climate and remote sensing models as well as the retrieval accuracy of some satellite products.

The energy delivered to the land surface via insolation is a primary driver of evapotranspiration (ET)—the exchange of water vapor between the land and atmosphere. Spatially distributed ET products are in great demand in the water resource management community for real-time operations and sustainable water use planning. The accuracy and deliverability of these products are determined in part by the characteristics and quality of the insolation data sources used as input to the ET models. This paper investigates the practical utility of three different insolation datasets within the context of a satellite-based remote sensing framework for mapping ET at high spatiotemporal resolution, in an application over the Sacramento⁻San Joaquin Delta region in California. The datasets tested included one reanalysis product: The Climate System Forecast Reanalysis (CFSR) at 0.25° spatial resolution, and two remote sensing insolation products generated with geostationary satellite imagery: a product for the continental United States at 0.2°, developed by the University of Wisconsin Space Sciences and Engineering Center (SSEC) and a coarser resolution (1°) global Clouds and the Earth’s Radiant Energy System (CERES) product. The three insolation data sources were compared to pyranometer data collected at flux towers within the Delta region to establish relative accuracy. The satellite products significantly outperformed CFSR, with root-mean square errors (RMSE) of 2.7, 1.5, and 1.4 MJ·m−2·d−1 for CFSR, CERES, and SSEC, respectively, at daily timesteps. The satellite-based products provided more accurate estimates of cloud occurrence and radiation transmission, while the reanalysis tended to underestimate solar radiation under cloudy-sky conditions. However, this difference in insolation performance did not translate into comparable improvement in the ET retrieval accuracy, where the RMSE in daily ET was 0.98 and 0.94 mm d−1 using the CFSR and SSEC insolation data sources, respectively, for all the flux sites combined. The lack of a notable impact on the aggregate ET performance may be due in part to the predominantly clear-sky conditions prevalent in central California, under which the reanalysis and satellite-based insolation data sources have comparable accuracy. While satellite-based insolation data could improve ET retrieval in more humid regions with greater cloud-cover frequency, over the California Delta and climatologically similar regions in the western U.S., the CFSR data may suffice for real-time ET modeling efforts.

Real-time monitoring of crop phenology is critical for assisting farmers managing crop growth and yield estimation. In this study, we presented an approach to monitor in real time crop phenology using timely available daily Visible Infrared Imaging Radiometer Suite (VIIRS) observations and historical Moderate Resolution Imaging Spectroradiometer (MODIS) datasets in the Midwestern United States. MODIS data at a spatial resolution of 500 m from 2003 to 2012 were used to generate the climatology of vegetation phenology. By integrating climatological phenology and timely available VIIRS observations in 2014 and 2015, a set of temporal trajectories of crop growth development at a given time for each pixel were then simulated using a logistic model. The simulated temporal trajectories were used to identify spring green leaf development and predict the occurrences of greenup onset, mid-greenup phase, and maximum greenness onset using curvature change rate. Finally, the accuracy of real-time monitoring from VIIRS observations was evaluated by comparing with summary crop progress (CP) reports of ground observations from the National Agricultural Statistics Service (NASS) of the United States Department of Agriculture (USDA). The results suggest that real-time monitoring of crop phenology from VIIRS observations is a robust tool in tracing the crop progress across regional areas. In particular, the date of mid-greenup phase from VIIRS was significantly correlated to the planting dates reported in NASS CP for both corn and soybean with a consistent lag of 37 days and 27 days on average (p < 0.01), as well as the emergence dates in CP with a lag of 24 days and 16 days on average (p < 0.01), respectively. The real-time monitoring of maximum greenness onset from VIIRS was able to predict the corn silking dates with an advance of 9 days (p < 0.01) and the soybean blooming dates with a lag of 7 days on average (p < 0.01). These findings demonstrate the capability of VIIRS observations to effectively monitor temporal dynamics of crop progress in real time at a regional scale.

The utility of remote sensing data in crop yield modeling has typically been evaluated at the regional or state level using coarse resolution (>250 m) data. The use of medium resolution data (10–100 m) for yield estimation at field scales has been limited due to the low temporal sampling frequency characteristics of these sensors. Temporal sampling at a medium resolution can be significantly improved, however, when multiple remote sensing data sources are used in combination. Furthermore, data fusion approaches have been developed to blend data from different spatial and temporal resolutions. This paper investigates the impacts of improved temporal sampling afforded by multi-source datasets on our ability to explain spatial and temporal variability in crop yields in central Iowa (part of the U.S. Corn Belt). Several metrics derived from vegetation index (VI) time-series were evaluated using Landsat-MODIS fused data from 2001 to 2015 and Landsat-Sentinel2-MODIS fused data from 2016 and 2017. The fused data explained the yield variability better, with a higher coefficient of determination (R2) and a smaller relative mean absolute error than using a single data source alone. In this study area, the best period for the yield prediction for corn and soybean was during the middle of the growing season from day 192 to 236 (early July to late August, 1–3 months before harvest). These findings emphasize the importance of high temporal and spatial resolution remote sensing data in agricultural applications.

Monitoring of aboveground net primary production (ANPP) is critical for effective management of rangeland ecosystems but is problematic due to the vast extent of rangelands globally, and the high costs of ground-based measurements. Remote sensing of absorbed photosynthetically active radiation (APAR) can be used to predict ANPP, potentially offering an alternative means of quantifying ANPP at both high temporal and spatial resolution across broad spatial extents. The relationship between ANPP and APAR has often been quantified based on either spatial variation across a broad region or temporal variation at a location over time, but rarely both. Here we assess: (i) if the relationship between ANPP and APAR is consistent when evaluated across time and space; (ii) potential factors driving differences between temporal versus spatial models, and (iii) the magnitude of potential errors relating to space for time transformations in quantifying productivity. Using two complimentary ANPP datasets and remotely sensed data derived from MODIS and a Landsat/MODIS fusion data product, we find that slopes of spatial models are generally greater than slopes of temporal models. The abundance of plant species with different structural attributes, specifically the abundance of C4 shortgrasses with prostrate canopies versus taller, more productive C3 species with more vertically complex canopies, tended to vary more dramatically in space than over time. This difference in spatial versus temporal variation in these key plant functional groups appears to be the primary driver of differences in slopes among regression models. While the individual models revealed strong relationships between ANPP to APAR, the use of temporal models to predict variation in space (or vice versa) can increase error in remotely sensed predictions of ANPP.

Thermal infrared (TIR) imagery is normally acquired at coarser pixel resolution than that of shortwave sensors on the same satellite platform and often the TIR resolution is not suitable for monitoring crop conditions of individual fields or the impacts of land cover changes that are at significantly finer spatial scales. Consequently, thermal sharpening techniques have been developed to sharpen TIR imagery to shortwave band pixel resolutions, which are often fine enough for field-scale applications. A classic thermal sharpening technique, TsHARP, uses a relationship between land surface temperature (LST) and Normalized Difference Vegetation Index (NDVI) developed empirically at the TIR pixel resolution and applied at the NDVI pixel resolution. However, recent studies show that unique relationships between temperature and NDVI may only exist for a limited class of landscapes, with mostly green vegetation and homogeneous air and soil conditions. To extend application of thermal sharpening to more complex conditions, a new data mining sharpener (DMS) technique is developed. The DMS approach builds regression trees between TIR band brightness temperatures and shortwave spectral reflectances based on intrinsic sample characteristics. A comparison of sharpening techniques applied over a rainfed agricultural area in central Iowa, an irrigated agricultural region in the Texas High Plains, and a heterogeneous naturally vegetated landscape in Alaska indicates that the DMS outperformed TsHARP in all cases. The artificial box-like patterns in LST generated by the TsHARP approach are greatly reduced using the DMS scheme, especially for areas containing irrigated crops, water bodies, thin clouds or terrain. While the DMS technique can provide fine resolution TIR imagery, there are limits to the sharpening ratios that can be reasonably implemented. Consequently, sharpening techniques cannot replace actual thermal band imagery at fine resolutions or missions that provide high quality thermal band imagery at high temporal and spatial resolution critical for many agricultural, land use and water resource management applications.

Hyperspectral image classification has been acknowledged as the fundamental and challenging task of hyperspectral data processing. The abundance of spectral and spatial information has provided great opportunities to effectively characterize and identify ground materials. In this paper, we propose a spectral and spatial classification framework for hyperspectral images based on Random Multi-Graphs (RMGs). The RMG is a graph-based ensemble learning method, which is rarely considered in hyperspectral image classification. It is empirically verified that the semi-supervised RMG deals well with small sample setting problems. This kind of problem is very common in hyperspectral image applications. In the proposed method, spatial features are extracted based on linear prediction error analysis and local binary patterns; spatial features and spectral features are then stacked into high dimensional vectors. The high dimensional vectors are fed into the RMG for classification. By randomly selecting a subset of features to create a graph, the proposed method can achieve excellent classification performance. The experiments on three real hyperspectral datasets have demonstrated that the proposed method exhibits better performance than several closely related methods.

Leaf area index (LAI) is a critical vegetation structural parameter in biogeochemical and biophysical ecosystems. High-resolution LAI products play an essential role in regional studies. Empirical methods, which normally use field measurements as their training samples and have been identified as the most commonly used approaches to retrieve structural parameters of vegetation from high-resolution remote-sensing data, are limited by the quality of training samples. Few efforts have been made to generate training samples from existing global LAI products. In this study, two methods (a homogeneous and pure pixel filter method (method A) and a pixel unmixing method (method B)) were developed to extract training samples from moderate-resolution imaging spectroradiometer (MODIS) surface reflectance and LAI products, and a support vector regression (SVR) algorithm trained by the samples was used to retrieve the high-resolution LAI from Landsat data at Baoding, situated in the Hebei Province in China, and Des Moines, situated in Iowa, United States. For the homogeneous and pure pixel filter method, two different sets of training samples were designed. One was composed of upscaled Landsat reflectance at the 500-m resolution and MODIS LAI products (dataset A1); the other was composed of MODIS reflectance and LAI products (dataset A2). With them, two inversion models were developed using SVR. For the pixel unmixing method, the training samples (dataset B) were extracted from unmixed MODIS surface reflectance and LAI products at 30-m resolution, and the third inversion model was obtained with them. LAI inversion results showed that good agreement with field measurements was achieved using these three inversion models. The R2 (coefficient of determination) value and the root mean square error (RMSE) value were computed to assess the results. For all tests, the R2 values are higher than 0.74 and RMSE values are less than 0.73. These tests showed that three models for the two methods combined with MODIS products can retrieve 30-m resolution LAI from Landsat data. The results of the pixel unmixing method was slightly better than that of the homogeneous and pure pixel filter method.

Spatial and temporal data fusion approaches have been developed to fuse reflectance imagery from Landsat and the Moderate Resolution Imaging Spectroradiometer (MODIS), which have complementary spatial and temporal sampling characteristics. The approach relies on using Landsat and MODIS image pairs that are acquired on the same day to estimate Landsat-scale reflectance on other MODIS dates. Previous studies have revealed that the accuracy of data fusion results partially depends on the input image pair used. The selection of the optimal image pair to achieve better prediction of surface reflectance has not been fully evaluated. This paper assesses the impacts of Landsat-MODIS image pair selection on the accuracy of the predicted land surface reflectance using the Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM) over different landscapes. MODIS images from the Aqua and Terra platforms were paired with images from the Landsat 7 Enhanced Thematic Mapper Plus (ETM+) and Landsat 8 Operational Land Imager (OLI) to make different pair image combinations. The accuracy of the predicted surface reflectance at 30 m resolution was evaluated using the observed Landsat data in terms of mean absolute difference, root mean square error and correlation coefficient. Results show that the MODIS pair images with smaller view zenith angles produce better predictions. As expected, the image pair closer to the prediction date during a short prediction period produce better prediction results. For prediction dates distant from the pair date, the predictability depends on the temporal and spatial variability of land cover type and phenology. The prediction accuracy for forests is higher than for crops in our study areas. The Normalized Difference Vegetation Index (NDVI) for crops is overestimated during the non-growing season when using an input image pair from the growing season, while NDVI is slightly underestimated during the growing season when using an image pair from the non-growing season. Two automatic pair selection strategies are evaluated. Results show that the strategy of selecting the MODIS pair date image that most highly correlates with the MODIS image on the prediction date produces more accurate predictions than the nearest date strategy. This study demonstrates that data fusion results can be improved if appropriate image pairs are used.

The ability to accurately monitor and anticipate changes in consumptive water use associated with changing land use and land management is critical to developing sustainable water management strategies in water-limited climatic regions. In this paper, we present an application of a remote sensing data fusion technique for developing high spatiotemporal resolution maps of evapotranspiration (ET) at scales that can be associated with changes in land use. The fusion approach combines ET map timeseries developed using an multi-scale energy balance algorithm applied to thermal data from Earth observation platforms with high spatial but low temporal resolution (e.g., Landsat) and with moderate resolution but frequent temporal coverage (e.g., MODIS (Moderate Resolution Imaging Spectroradiometer)). The approach is applied over the Sacramento-San Joaquin Delta region in California—an area critical to both agricultural production and drinking water supply within the state that has recently experienced stresses on water resources due to a multi-year (2012–2017) extreme drought. ET “datacubes” with 30-m resolution and daily timesteps were constructed for the 2015–2016 water years and related to detailed maps of land use developed at the same spatial scale. The ET retrievals are evaluated at flux sites over multiple land covers to establish a metric of accuracy in the annual water use estimates, yielding root-mean-square errors of 1.0, 0.8, and 0.3 mm day−1 at daily, monthly, and yearly timesteps, respectively, for all sites combined. Annual ET averaged over the Delta changed only 3 mm year−1 between water years, from 822 to 819 mm year−1, translating to an area-integrated total change in consumptive water use of seven thousand acre-feet (TAF). Changes were largest in areas with recorded land-use change between water years—most significantly, fallowing of crop land presumably in response to reductions in water availability and allocations due to the drought. Moreover, the time evolution in water use associated with wetland restoration—an effort aimed at reducing subsidence and carbon emissions within the inner Delta—is assessed using a sample wetland chronosequence. Region-specific matrices of consumptive water use associated with land use changes may be an effective tool for policymakers and farmers to understand how land use conversion could impact consumptive use and demand.

We present a new, simple, and efficient approach to fusing MODIS and Landsat images. It is well known that MODIS images have high temporal resolution and low spatial resolution, whereas Landsat images are just the opposite. Similar to earlier approaches, our goal is to fuse MODIS and Landsat images to yield high spatial and high temporal resolution images. Our approach consists of two steps. First, a mapping is established between two MODIS images, where one is at an earlier time, t1, and the other one is at the time of prediction, tp. Second, this mapping is applied to map a known Landsat image at t1 to generate a predicted Landsat image at tp. Similar to the Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM), SpatioTemporal Image-Fusion Model (STI-FM), and the Flexible Spatiotemporal DAta Fusion (FSDAF) approaches, only one pair of MODIS and Landsat images is needed for prediction. Using seven performance metrics, experiments involving actual Landsat and MODIS images demonstrated that the proposed approach achieves comparable or better fusion performance than that of STARFM, STI-FM, and FSDAF.

With the development of Earth observation programs, more and more multi-temporal synthetic aperture radar (SAR) data are available from remote sensing platforms. Therefore, it is demanding to develop unsupervised methods for SAR image change detection. Recently, deep learning-based methods have displayed promising performance for remote sensing image analysis. However, these methods can only provide excellent performance when the number of training samples is sufficiently large. In this paper, a novel simple method for SAR image change detection is proposed. The proposed method uses two singular value decomposition (SVD) analyses to learn the non-linear relations between multi-temporal images. By this means, the proposed method can generate more representative feature expressions with fewer samples. Therefore, it provides a simple yet effective way to be designed and trained easily. Firstly, deep semi-nonnegative matrix factorization (Deep Semi-NMF) is utilized to select pixels that have a high probability of being changed or unchanged as samples. Next, image patches centered at these sample pixels are generated from the input multi-temporal SAR images. Then, we build SVD networks, which are comprised of two SVD convolutional layers and one histogram feature generation layer. Finally, pixels in both multi-temporal SAR images are classified by the SVD networks, and then the final change map can be obtained. The experimental results of three SAR datasets have demonstrated the effectiveness and robustness of the proposed method.

Understanding the effects that the Urban Heat Island (UHI) has on plant phenology is important in predicting ecological impacts of expanding cities and the impacts of the projected global warming. However, the underlying methods to monitor phenological events often limit this understanding. Generally, one can either have a small sample of in situ measurements or use satellite data to observe large areas of land surface phenology (LSP). In the latter, a tradeoff exists among platforms with some allowing better temporal resolution to pick up discrete events and others possessing the spatial resolution appropriate for observing heterogeneous landscapes, such as urban areas. To overcome these limitations, we applied the Spatial and Temporal Adaptive Reflectance Model (STARFM) to fuse Landsat surface reflectance and MODIS nadir BRDF-adjusted reflectance (NBAR) data with three separate selection conditions for input data across two versions of the software. From the fused images, we derived a time-series of high temporal and high spatial resolution synthetic Normalized Difference Vegetation Index (NDVI) imagery to identify the dates of the start of the growing season (SOS), end of the season (EOS), and the length of the season (LOS). The results were compared between the urban and exurban developed areas within the vicinity of Ogden, UT and across all three data scenarios. The results generally show an earlier urban SOS, later urban EOS, and longer urban LOS, with variation across the results suggesting that phenological parameters are sensitive to input changes. Although there was strong evidence that STARFM has the potential to produce images capable of capturing the UHI effect on phenology, we recommend that future work refine the proposed methods and compare the results against ground events.

Land surface temperature (LST) is an important parameter that is highly responsive to surface energy fluxes and has become valuable to many disciplines. However, it is difficult to acquire satellite LSTs with both high spatial and temporal resolutions due to tradeoffs between them. Thus, various algorithms/models have been developed to enhance the spatial or the temporal resolution of thermal infrared (TIR) data or LST, but rarely both. The Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM) is the widely-used data fusion algorithm for Landsat and MODIS imagery to produce Landsat-like surface reflectance. In order to extend the STARFM application over heterogeneous areas, an enhanced STARFM (ESTARFM) approach was proposed by introducing a conversion coefficient and the spectral unmixing theory. The aim of this study is to conduct a comprehensive evaluation of the ESTARFM algorithm for generating ASTER-like daily LST by three approaches: simulated data, ground measurements and remote sensing products, respectively. The datasets of LST ground measurements, MODIS, and ASTER images were collected in an arid region of Northwest China during the first thematic HiWATER-Multi-Scale Observation Experiment on Evapotranspiration (MUSOEXE) over heterogeneous land surfaces in 2012 from May to September. Firstly, the results of the simulation test indicated that ESTARFM could accurately predict background with temperature variations, even coordinating with small ground objects and linear ground objects. Secondly, four temporal ASTER and MODIS data fusion LSTs (i.e., predicted ASTER-like LST products) were highly consistent with ASTER LST products. Here, the four correlation coefficients were greater than 0.92, root mean square error (RMSE) reached about 2 K and mean absolute error (MAE) ranged from 1.32 K to 1.73 K. Finally, the results of the ground measurement validation indicated that the overall accuracy was high (R2 = 0.92, RMSE = 0.77 K), and the ESTARFM algorithm is a highly recommended method to assemble time series images at ASTER spatial resolution and MODIS temporal resolution due to LST estimation error less than 1 K. However, the ESTARFM method is also limited in predicting LST changes that have not been recorded in MODIS and/or ASTER pixels.