Remote Sensing — Open Access Journal

Monitoring and forecasting crop yields is a critical component of understanding and better addressing global food security challenges. Detailed spatial information on crop-type distribution is fundamental for in-season crop condition monitoring and yields forecasting over large agricultural areas, as it enables the extraction of crop-specific signals. Yet, the availability of such data within the growing season is often limited. Within this context, this study seeks to develop a practical approach to extract a crop-specific signal for yield forecasting in cases where crop rotations are prevalent, and detailed in-season information on crop type distribution is not available. We investigated the possibility of accurately forecasting winter wheat yields by using a counter-intuitive approach, which coarsens the spatial resolution of out-of-date detailed winter wheat masks and uses them in combination with easily accessibly coarse spatial resolution remotely sensed time series data. The main idea is to explore an optimal spatial resolution at which crop type changes will be negligible due to crop rotation (so a previous seasons’ mask, which is more readily available can be used) and an informative signal can be extracted, so it can be correlated to crop yields. The study was carried out in the United States of America (USA) and utilized multiple years of NASA Moderate Resolution Imaging Spectroradiometer (MODIS) data, US Department of Agriculture (USDA) National Agricultural Statistics Service (NASS) detailed wheat masks, and a regression-based winter wheat yield model. The results indicate that, in places where crop rotations were prevalent, coarsening the spatial scale of a crop type mask from the previous season resulted in a constant per-pixel wheat proportion over multiple seasons. This enables the consistent extraction of a crop-specific vegetation index time series that can be used for in-season monitoring and yield estimation over multiple years using a single mask. In the case of the USA, using a moderate resolution crop type mask from a previous season aggregated to 5 km resolution, resulted in a 0.7% tradeoff in accuracy relative to the control case where annually-updated detailed crop-type masks were available. These findings suggest that when detailed in-season data is not available, winter wheat yield can be accurately forecasted (within 10%) prior to harvest using a single, prior season crop mask and coarse resolution Normalized Difference Vegetation Index (NDVI) time series data. Full article

The height of F2 peak (hmF2) is an essential ionospheric parameter and its variations can reflect both the earth magnetic and solar activities. Therefore, reliable prediction of hmF2 is important for the study of space, such as solar wind and extreme weather events. However, most current models are unable to forecast the variation of the ionosphere effectively since real-time measurements are required as model inputs. In this study, a new Australian regional hmF2 forecast model was developed by using ionosonde measurements and the bidirectional Long Short-Term Memory (bi-LSTM) method. The hmF2 value in the next hour can be predicted using the data from the past five hours at the same location. The inputs chosen from a location of interest include month of the year, local time (LT), $K_p$, $F_{10.7}$ and hmF2 as an independent variable vector. The independent variable vectors in the immediate past five hours are considered as an independent variable set, which is used as an input of the new Australian regional hmF2 forecast model developed for the prediction of hmF2 in the hour to come. The performance of the new model developed is evaluated by comparing with those from other popular models, such as the AMTB, Shubin, ANN and LSTM models. Results showed that: (1) the new model can substantially outperform all the other four models. (2) Compared to the LSTM model, the new model is proven to be more robust and rapidly convergent. The mew model also outperforms that of the ANN model by around 30%. (3) the minimum sample number for the bi-LSTM method (i.e., 2000) to converge is about 50% less than that is required for the LSTM method (i.e., 3000). (4) Compared to the Shubin model, the bi-LSTM method can effectively forecast the hmF2 values up to 5 h. This research is a first attempt at using the deep learning-based method for the application of the ionospheric prediction. Full article

Crop residues serve many important functions in agricultural conservation including preserving soil moisture, building soil organic carbon, and preventing erosion. Percent crop residue cover on a field surface reflects the outcome of tillage intensity and crop management practices. Previous studies using proximal hyperspectral remote sensing have demonstrated accurate measurement of percent residue cover using residue indices that characterize cellulose and lignin absorption features found between 2100 nm and 2300 nm in the shortwave infrared (SWIR) region of the electromagnetic spectrum. The 2014 launch of the WorldView-3 (WV3) satellite has now provided a space-borne platform for the collection of narrow band SWIR reflectance imagery capable of measuring these cellulose and lignin absorption features. In this study, WorldView-3 SWIR imagery (14 May 2015) was acquired over farmland on the Eastern Shore of Chesapeake Bay (Maryland, USA), was converted to surface reflectance, and eight different SWIR reflectance indices were calculated. On-farm photographic sampling was used to measure percent residue cover at a total of 174 locations in 10 agricultural fields, ranging from plow-till to continuous no-till management, and these in situ measurements were used to develop percent residue cover prediction models from the SWIR indices using both polynomial and linear least squares regressions. Analysis was limited to agricultural fields with minimal green vegetation (Normalized Difference Vegetation Index < 0.3) due to expected interference of vegetation with the SWIR indices. In the resulting residue prediction models, spectrally narrow residue indices including the Shortwave Infrared Normalized Difference Residue Index (SINDRI) and the Lignin Cellulose Absorption Index (LCA) were determined to be more accurate than spectrally broad Landsat-compatible indices such as the Normalized Difference Tillage Index (NDTI), as determined by respective R² values of 0.94, 0.92, and 0.84 and respective residual mean squared errors (RMSE) of 7.15, 8.40, and 12.00. Additionally, SINDRI and LCA were more resistant to interference from low levels of green vegetation. The model with the highest correlation (2nd order polynomial SINDRI, R² = 0.94) was used to convert the SWIR imagery into a map of crop residue cover for non-vegetated agricultural fields throughout the imagery extent, describing the distribution of tillage intensity within the farm landscape. WorldView-3 satellite imagery provides spectrally narrow SWIR reflectance measurements that show utility for a robust mapping of crop residue cover. Full article

Over the past two decades, persistent occurrences of harmful algal blooms (HAB; Karenia brevis) have been reported in Charlotte County, southwestern Florida. We developed data-driven models that rely on spatiotemporal remote sensing and field data to identify factors controlling HAB propagation, provide a same-day distribution (nowcasting), and forecast their occurrences up to three days in advance. We constructed multivariate regression models using historical HAB occurrences (213 events reported from January 2010 to October 2017) compiled by the Florida Fish and Wildlife Conservation Commission and validated the models against a subset (20%) of the historical events. The models were designed to capture the onset of the HABs instead of those that developed days earlier and continued thereafter. A prototype of an early warning system was developed through a threefold exercise. The first step involved the automatic downloading and processing of daily Moderate Resolution Imaging Spectroradiometer (MODIS) Aqua products using SeaDAS ocean color processing software to extract temporal and spatial variations of remote sensing-based variables over the study area. The second step involved the development of a multivariate regression model for same-day mapping of HABs and similar subsequent models for forecasting HAB occurrences one, two, and three days in advance. Eleven remote sensing variables and two non-remote sensing variables were used as inputs for the generated models. In the third and final step, model outputs (same-day and forecasted distribution of HABs) were posted automatically on a web map. Our findings include: (1) the variables most indicative of the timing of bloom propagation are bathymetry, euphotic depth, wind direction, sea surface temperature (SST), ocean chlorophyll three-band algorithm for MODIS [chlorophyll-a OC3M] and distance from the river mouth, and (2) the model predictions were 90% successful for same-day mapping and 65%, 72% and 71% for the one-, two- and three-day advance predictions, respectively. The adopted methodologies are reliable at a local scale, dependent on readily available remote sensing data, and cost-effective and thus could potentially be used to map and forecast algal bloom occurrences in data-scarce regions. Full article

The quality control of remote sensing reflectance (R_rs) is a challenging task in remote sensing applications, mainly in the retrieval of accurate in situ measurements carried out in optically complex aquatic systems. One of the main challenges is related to glint effect into the in situ measurements. Our study evaluates four different methods to reduce the glint effect from the R_rs spectra collected in cascade reservoirs with widely differing optical properties. The first (i) method adopts a constant coefficient for skylight correction (ρ) for any geometry viewing of in situ measurements and wind speed lower than 5 m·s⁻¹; (ii) the second uses a look-up-table with variable ρ values accordingly to viewing geometry acquisition and wind speed; (iii) the third method is based on hyperspectral optimization to produce a spectral glint correction, and (iv) computes ρ as a function of wind speed. The glint effect corrected R_rs spectra were assessed using HydroLight simulations. The results showed that using the glint correction with spectral ρ achieved the lowest errors, however, in a Colored Dissolved Organic Matter (CDOM) dominated environment with no remarkable chlorophyll-a concentrations, the best method was the second. Besides, the results with spectral glint correction reduced almost 30% of errors. Full article

Fire Spread Rate (FSR) can indicate how fast a fire is spreading, which is especially helpful for wildfire rescue and management. Historically, images obtained from sun-orbiting satellites such as Moderate Resolution Imaging Spectroradiometer (MODIS) were used to detect active fire and burned area at the large spatial scale. However, the daily revisit cycles make them inherently unable to extract FSR in near real­-time (hourly or less). We argue that the Himawari-8, a next generation geostationary satellite with a 10-min temporal resolution and 0.5–2 km spatial resolution, may have the potential for near real-time FSR extraction. To that end, we propose a novel method (named H8-FSR) for near real-time FSR extraction based on the Himawari-8 data. The method first defines the centroid of the burned area as the fire center and then the near real-time FSR is extracted by timely computing the movement rate of the fire center. As a case study, the method was applied to the Esperance bushfire that broke out on 17 November, 2015, in Western Australia. Compared with the estimated FSR using the Commonwealth Scientific and Industrial Research Organization (CSIRO) Grassland Fire Spread (GFS) model, H8-FSR achieved favorable performance with a coefficient of determination (R²) of 0.54, mean bias error of –0.75 m/s, mean absolute percent error of 33.20% and root mean square error of 1.17 m/s, respectively. These results demonstrated that the Himawari-8 data are valuable for near real-time FSR extraction, and also suggested that the proposed method could be potentially applicable to other next generation geostationary satellite data. Full article

Landscapes display overlapping sets of correlations in different regions at different spatial scales, and these correlations can be delineated by pattern analysis. This study identified the correlations between landscape pattern and topography at various scales and locations in urban-rural profiles from Jilin City, China, using Pearson correlation analysis and wavelet method. Two profiles, 30 km (A) and 35 km (B) in length with 0.1-km sampling intervals, were selected. The results indicated that profile A was more sensitive to the characterization of the land use pattern as influenced by topography due to its more varied terrain, and three scales (small, medium, and large) could be defined based on the variation in the standard deviation of the wavelet coherency in profile A. Correlations between landscape metrics and elevation were similar at large scales (over 8 km), while complex correlations were discovered at other scale intervals. The medium scale of cohesion and Shannon’s diversity index was 1–8 km, while those of perimeter-area fractal dimension and edge density index were 1.5–8 km and 2–8 km, respectively. At small scales, the correlations were weak as a whole and scattered due to the micro-topography and landform elements, such as valleys and hillsides. At medium scales, the correlations were most affected by local topography, and the land use pattern was significantly correlated with topography at several locations. At large spatial scales, significant correlation existed throughout the study area due to alternating mountains and plains. In general, the strength of correlation between landscape metrics and topography increased gradually with increasing spatial scale, although this tendency had some fluctuations in several locations. Despite a complex calculating process and ecological interpretation, the wavelet method is still an effective tool to identify multi-scale characteristics in landscape ecology. Full article

Images obtained in an underwater environment are often affected by colour casting and suffer from poor visibility and lack of contrast. In the literature, there are many enhancement algorithms that improve different aspects of the underwater imagery. Each paper, when presenting a new algorithm or method, usually compares the proposed technique with some alternatives present in the current state of the art. There are no studies on the reliability of benchmarking methods, as the comparisons are based on various subjective and objective metrics. This paper would pave the way towards the definition of an effective methodology for the performance evaluation of the underwater image enhancement techniques. Moreover, this work could orientate the underwater community towards choosing which method can lead to the best results for a given task in different underwater conditions. In particular, we selected five well-known methods from the state of the art and used them to enhance a dataset of images produced in various underwater sites with different conditions of depth, turbidity, and lighting. These enhanced images were evaluated by means of three different approaches: objective metrics often adopted in the related literature, a panel of experts in the underwater field, and an evaluation based on the results of 3D reconstructions. Full article

Several sectors need global horizontal irradiance (GHI) data for various purposes. However, the availability of a long-term time series of high quality in situ GHI measurements is limited. Therefore, several studies have tried to estimate GHI by re-analysing climate data or satellite images. Validation is essential for the later use of GHI data in the regions with a scarcity of ground-recorded data. This study contributes to previous studies that have been carried out in the past to validate HelioClim-3 version 5 (HC3v5) and the Copernicus Atmosphere Monitoring Service, using radiation service version 3 (CRSv3) data of hourly GHI from satellite-derived datasets (SDD) with nine ground stations in northeast Iraq, which have not been used previously. The validation is carried out with station data at the pixel locations and two other data points in the vicinity of each station, which is something that is rarely seen in the literature. The temporal and spatial trends of the ground data are well captured by the two SDDs. Correlation ranges from 0.94 to 0.97 in all-sky and clear-sky conditions in most cases, while for cloudy-sky conditions, it is between 0.51–0.72 and 0.82–0.89 for the clearness index. The bias is negative for most of the cases, except for three positive cases. It ranges from −7% to 4%, and −8% to 3% for the all-sky and clear-sky conditions, respectively. For cloudy-sky conditions, the bias is positive, and differs from one station to another, from 16% to 85%. The root mean square error (RMSE) ranges between 12–20% and 8–12% for all-sky and clear-sky conditions, respectively. In contrast, the RMSE range is significantly higher in cloudy-sky conditions: above 56%. The bias and RMSE for the clearness index are nearly the same as those for the GHI for all-sky conditions. The spatial variability of hourly GHI SDD differs only by 2%, depending on the station location compared to the data points around each station. The variability of two SDDs is quite similar to the ground data, based on the mean and standard deviation of hourly GHI in a month. Having station data at different timescales and the small number of stations with GHI records in the region are the main limitations of this analysis. Full article

Despite the importance of high-resolution population distribution in urban planning, disaster prevention and response, region economic development, and improvement of urban habitant environment, traditional urban investigations mainly focused on large-scale population spatialization by using coarse-resolution nighttime light (NTL) while few efforts were made to fine-resolution population mapping. To address problems of generating small-scale population distribution, this paper proposed a method based on the Random Forest Regression model to spatialize a 25 m population from the International Space Station (ISS) photography and urban function zones generated from social sensing data—point-of-interest (POI). There were three main steps, namely HSL (hue saturation lightness) transformation and saturation calibration of ISS, generating functional-zone maps based on point-of-interest, and spatializing population based on the Random Forest model. After accuracy assessments by comparing with WorldPop, the proposed method was validated as a qualified method to generate fine-resolution population spatial maps. In the discussion, this paper suggested that without help of auxiliary data, NTL cannot be directly employed as a population indicator at small scale. The Variable Importance Measure of the RF model confirmed the correlation between features and population and further demonstrated that urban functions performed better than LULC (Land Use and Land Cover) in small-scale population mapping. Urban height was also shown to improve the performance of population disaggregation due to its compensation of building volume. To sum up, this proposed method showed great potential to disaggregate fine-resolution population and other urban socio-economic attributes. Full article

Recently, convolutional neural networks (CNN) have been intensively investigated for the classification of remote sensing data by extracting invariant and abstract features suitable for classification. In this paper, a novel framework is proposed for the fusion of hyperspectral images and LiDAR-derived elevation data based on CNN and composite kernels. First, extinction profiles are applied to both data sources in order to extract spatial and elevation features from hyperspectral and LiDAR-derived data, respectively. Second, a three-stream CNN is designed to extract informative spectral, spatial, and elevation features individually from both available sources. The combination of extinction profiles and CNN features enables us to jointly benefit from low-level and high-level features to improve classification performance. To fuse the heterogeneous spectral, spatial, and elevation features extracted by CNN, instead of a simple stacking strategy, a multi-sensor composite kernels (MCK) scheme is designed. This scheme helps us to achieve higher spectral, spatial, and elevation separability of the extracted features and effectively perform multi-sensor data fusion in kernel space. In this context, a support vector machine and extreme learning machine with their composite kernels version are employed to produce the final classification result. The proposed framework is carried out on two widely used data sets with different characteristics: an urban data set captured over Houston, USA, and a rural data set captured over Trento, Italy. The proposed framework yields the highest OA of $92.57\%$ and $97.91\%$ for Houston and Trento data sets. Experimental results confirm that the proposed fusion framework can produce competitive results in both urban and rural areas in terms of classification accuracy, and significantly mitigate the salt and pepper noise in classification maps. Full article

Fractional vegetation cover (FVC) is an essential input parameter for many environmental and ecological models. Recently, several global FVC products have been generated using remote sensing data. The Global LAnd Surface Satellite (GLASS) FVC product, which is generated from Moderate Resolution Imaging Spectroradiometer (MODIS) data, has attained acceptable performance. However, the original MODIS operation design lifespan has been exceeded. The Visible Infrared Imaging Radiometer Suite (VIIRS) onboard the Suomi National Polar-Orbiting Partnership (S-NPP) satellite was designed to be the MODIS successor. Therefore, developing an FVC estimation algorithm for VIIRS data is important for maintaining continuous FVC estimates in case of MODIS failure. In this study, a global FVC estimation algorithm for VIIRS surface reflectance data was proposed based on machine learning methods, which investigated the performances of back propagating neural networks (BPNNs), general regression networks (GRNNs), multivariate adaptive regression splines (MARS), and Gaussian process regression (GPR). The training samples were extracted from the GLASS FVC product and corresponding reconstructed VIIRS surface reflectance in 2013 over the global sampling locations. The VIIRS reflectances of red and near infrared (NIR) bands were the input variables for these machine learning methods. The theoretical performances and independent validation results indicated that the four machine learning methods could achieve similar and reliable FVC estimates. Regarding the FVC estimation accuracy, the GPR method achieved the best performance (R² = 0.9019, RMSE = 0.0887). The MARS method had the obvious advantage of computational efficiency. Furthermore, the FVC estimates achieved good spatial and temporal continuities. Therefore, the proposed FVC estimation algorithm for VIIRS data can potentially generate reliable global FVC data for related applications. Full article

Current space-based SAR offers unique opportunities to classify vegetation types and to monitor vegetation growth due to its frequent acquisitions and its sensitivity to vegetation geometry. However, SAR signals also experience frequent temporal fluctuations caused by precipitation events, complicating the mapping and monitoring of vegetation. In this paper, we show that the influence of a priori known precipitation events on the signals can be used advantageously for the classification of vegetation conditions. For this, we exploit the change in Sentinel-1 backscatter response between consecutive acquisitions under varying wetness conditions, which we show is dependent on the state of vegetation. The performance further improves when a priori information on the soil type is taken into account. Full article

Remote sensing is an important means to monitor the dynamics of the earth surface. It is still challenging for single-sensor systems to provide spatially high resolution images with high revisit frequency because of the technological limitations. Spatiotemporal fusion is an effective approach to obtain remote sensing images high in both spatial and temporal resolutions. Though dictionary learning fusion methods appear to be promising for spatiotemporal fusion, they do not consider the structure similarity between spectral bands in the fusion task. To capitalize on the significance of this feature, a novel fusion model, named the adaptive multi-band constraints fusion model (AMCFM), is formulated to produce better fusion images in this paper. This model considers structure similarity between spectral bands and uses the edge information to improve the fusion results by adopting adaptive multi-band constraints. Moreover, to address the shortcomings of the ${\ell }_1$ norm which only considers the sparsity structure of dictionaries, our model uses the nuclear norm which balances sparsity and correlation by producing an appropriate coefficient in the reconstruction step. We perform experiments on real-life images to substantiate our conceptual augments. In the empirical study, the near-infrared (NIR), red and green bands of Landsat Enhanced Thematic Mapper Plus (ETM+) and Moderate Resolution Imaging Spectroradiometer (MODIS) are fused and the prediction accuracy is assessed by both metrics and visual effects. The experiments show that our proposed method performs better than state-of-the-art methods. It also sheds light on future research. Full article

Background: Crown fires are often intense and fast spreading and hence can have serious impacts on soil, vegetation, and wildlife habitats. Fire managers try to prevent the initiation and spread of crown fires in forested landscapes through fuel management. The minimum fuel conditions necessary to initiate and propagate crown fires are known to be strongly influenced by four stand structural variables: surface fuel load (SFL), fuel strata gap (FSG), canopy base height (CBH), and canopy bulk density (CBD). However, there is often a lack of quantitative data about these variables, especially at the landscape scale. Methods: In this study, data from 123 sample plots established in pure, even-aged, Pinus radiata and Pinus pinaster stands in northwest Spain were analyzed. In each plot, an intensive field inventory was used to characterize surface and canopy fuels load and structure, and to estimate SFL, FSG, CBH, and CBD. Equations relating these variables to Sentinel-2A (S-2A) bands and vegetation indices were obtained using two non-parametric techniques: Random Forest (RF) and Multivariate Adaptive Regression Splines (MARS). Results: According to the goodness-of-fit statistics, RF models provided the most accurate estimates, explaining more than 12%, 37%, 47%, and 31% of the observed variability in SFL, FSG, CBH, and CBD, respectively. To evaluate the performance of the four equations considered, the observed and estimated values of the four fuel variables were used separately to predict the potential type of wildfire (surface fire, passive crown fire, or active crown fire) for each plot, considering three different burning conditions (low, moderate, and extreme). The results of the confusion matrix indicated that 79.8% of the surface fires and 93.1% of the active crown fires were correctly classified; meanwhile, the highest rate of misclassification was observed for passive crown fire, with 75.6% of the samples correctly classified. Conclusions: The results highlight that the combination of medium resolution imagery and machine learning techniques may add valuable information about surface and canopy fuel variables at large scales, whereby crown fire potential and the potential type of wildfire can be classified. Full article

Following the growing availability of low-cost, commercially available unmanned aerial vehicles (UAVs), more and more research efforts have been focusing on object tracking using videos recorded from UAVs. However, tracking from UAV videos poses many challenges due to platform motion, including background clutter, occlusion, and illumination variation. This paper tackles these challenges by proposing a correlation filter-based tracker with feature fusion and saliency proposals. First, we integrate multiple feature types such as dimensionality-reduced color name (CN) and histograms of oriented gradient (HOG) features to improve the performance of correlation filters for UAV videos. Yet, a fused feature acting as a multivector descriptor cannot be directly used in prior correlation filters. Therefore, a fused feature correlation filter is proposed that can directly convolve with a multivector descriptor, in order to obtain a single-channel response that indicates the location of an object. Furthermore, we introduce saliency proposals as re-detector to reduce background interference caused by occlusion or any distracter. Finally, an adaptive template-update strategy according to saliency information is utilized to alleviate possible model drifts. Systematic comparative evaluations performed on two popular UAV datasets show the effectiveness of the proposed approach. Full article

Accurate water mapping depends largely on the water index. However, most previously widely-adopted water index methods are developed from 30-m resolution Landsat imagery, with low-albedo commission error (e.g., shadow misclassified as water) and threshold instability being identified as the primary issues. Besides, since the shortwave-infrared (SWIR) spectral band (band 11) on Sentinel-2 is 20 m spatial resolution, current SWIR-included water index methods usually produce water maps at 20 m resolution instead of the highest 10 m resolution of Sentinel-2 bands, which limits the ability of Sentinel-2 to detect surface water at finer scales. This study aims to develop a water index from Sentinel-2 that improves native resolution and accuracy of water mapping at the same time. Support Vector Machine (SVM) is used to exploit the 10-m spectral bands among Sentinel-2 bands of three resolutions (10-m; 20-m; 60-m). The new Multi-Spectral Water Index (MuWI), consisting of the complete version and the revised version (MuWI-C and MuWI-R), is designed as the combination of normalized differences for threshold stability. The proposed method is assessed on coincident Sentinel-2 and sub-meter images covering a variety of water types. When compared to previous water indexes, results show that both versions of MuWI enable to produce native 10-m resolution water maps with higher classification accuracies (p-value < 0.01). Commission and omission errors are also significantly reduced particularly in terms of shadow and sunglint. Consistent accuracy over complex water mapping scenarios is obtained by MuWI due to high threshold stability. Overall, the proposed MuWI method is applicable to accurate water mapping with improved spatial resolution and accuracy, which possibly facilitates water mapping and its related studies and applications on growing Sentinel-2 images. Full article

A timely inventory of agricultural areas and crop types is an essential requirement for ensuring global food security and allowing early crop monitoring practices. Satellite remote sensing has proven to be an increasingly more reliable tool to identify crop types. With the Copernicus program and its Sentinel satellites, a growing source of satellite remote sensing data is publicly available at no charge. Here, we used joint Sentinel-1 radar and Sentinel-2 optical imagery to create a crop map for Belgium. To ensure homogenous radar and optical inputs across the country, Sentinel-1 12-day backscatter mosaics were created after incidence angle normalization, and Sentinel-2 normalized difference vegetation index (NDVI) images were smoothed to yield 10-daily cloud-free mosaics. An optimized random forest classifier predicted the eight crop types with a maximum accuracy of 82% and a kappa coefficient of 0.77. We found that a combination of radar and optical imagery always outperformed a classification based on single-sensor inputs, and that classification performance increased throughout the season until July, when differences between crop types were largest. Furthermore, we showed that the concept of classification confidence derived from the random forest classifier provided insight into the reliability of the predicted class for each pixel, clearly showing that parcel borders have a lower classification confidence. We concluded that the synergistic use of radar and optical data for crop classification led to richer information increasing classification accuracies compared to optical-only classification. Further work should focus on object-level classification and crop monitoring to exploit the rich potential of combined radar and optical observations. Full article

Lake ice is an important component in understanding the local climate as changes in temperature have an impact on the timing of key ice phenology events. In recent years, there has been a decline in the in-situ monitoring of lake ice events in Canada and microwave remote sensing imagery from synthetic aperture radar (SAR) is more widely used due to the high spatial resolution and response of backscatter to the freezing and melting of the ice surface. RADARSAT-2 imagery was used to develop a threshold-based method for determining lake ice events for mid-latitude lakes in Central Ontario from 2008 to 2017. Estimated lake ice phenology events are validated with ground-based observations and are compared against the Moderate Resolution Imaging Spectroradiometer (MODIS band 2). The threshold-based method was found to accurately identify 12 out of 17 freeze events and 13 out of 17 melt events from 2015–2017 when compared to ground-based observations. Mean absolute errors for freeze events ranged from 2.5 to 10.0 days when compared to MODIS imagery while the mean absolute error for water clear of ice (WCI) ranged from 1.5 to 7.1 days. The method is important for the study of mid-latitude lake ice due to its unique success in detecting multiple freeze and melting events throughout the ice season. Full article