Image Acquisition Dates Research Articles

Enhancing Pléiades-based crop mapping with multi-temporal and texture information

Accurate crop mapping using satellite imagery is crucial for improving the monitoring of agricultural landscapes. Very high resolution (VHR) satellite imagery offers unique capabilities in this respect, allowing for even small fields to be discerned and image texture analysis to be performed. Additionally, satellite imagery has greater efficiency than unmanned aerial vehicles due to its extensive coverage. Moreover, the operation flexibility of VHR satellites means that timely image acquisition is possible several times during the growing season. This study investigates the potential of VHR Pléiades images and the random forest classifier for accurate crop mapping. Four images acquired on April 9th, May 12th, May 31st, and June 20th were used to test 16 classification scenarios, including single-date and multi-temporal combinations of spectral bands, texture features, and vegetation Indices (VIs). The classification using the spectral bands from all four images achieved the highest overall accuracy, 93.9% and 96.3% at field and pixel levels, respectively. The bitemporal classifications had lower accuracy. Nevertheless, the combination of the May 12th and June 20th spectral bands had 90% accuracy, which indicated that two images may be sufficient for reliable mapping if the periods with phenological differences between crops are considered. Adding texture features to the spectral bands significantly enhanced the accuracy (up to 8%) of single-date classifications, making it highly recommended when only one image is available. However, the impact of texture was more pronounced on the later dates. It showed the most marked benefit for vineyards and alfalfa, with minimal or no improvement observed for other classes like winter barley. An additional increase in overall accuracy was achieved in three of the four dates by supplementing the spectral and texture bands with VIs. This study highlights the importance of considering image acquisition dates and crop types when designing satellite-based crop mapping strategies for optimal accuracy.

Monitoring Cover Crop Biomass in Southern Brazil Using Combined PlanetScope and Sentinel-1 SAR Data

Precision agriculture integrates multiple sensors and data types to support farmers with informed decision-making tools throughout crop cycles. This study evaluated Aboveground Biomass (AGB) estimates of Rye using attributes derived from PlanetScope (PS) optical, Sentinel-1 Synthetic Aperture Radar (SAR), and hybrid (optical plus SAR) datasets. Optical attributes encompassed surface reflectance from PS’s blue, green, red, and near-infrared (NIR) bands, alongside the Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI). Sentinel-1 SAR attributes included the C-band Synthetic Aperture Radar Ground Range Detected, VV and HH polarizations, and both Ratio and Polarization (Pol) indices. Ground reference AGB data for Rye (Secale cereal L.) were collected from 50 samples and four dates at a farm located in southern Brazil, aligning with image acquisition dates. Multiple linear regression models were trained and validated. AGB was estimated based on individual (optical PS or Sentinel-1 SAR) and combined datasets (optical plus SAR). This process was repeated 100 times, and variable importance was extracted. Results revealed improved Rye AGB estimates with integrated optical and SAR data. Optical vegetation indices displayed higher correlation coefficients (r) for AGB estimation (r = +0.67 for both EVI and NDVI) compared to SAR attributes like VV, Ratio, and polarization (r ranging from −0.52 to −0.58). However, the hybrid regression model enhanced AGB estimation (R2 = 0.62, p < 0.01), reducing RMSE to 579 kg·ha−1. Using only optical or SAR data yielded R2 values of 0.51 and 0.42, respectively (p < 0.01). In the hybrid model, the most important predictors were VV, NIR, blue, and EVI. Spatial distribution analysis of predicted Rye AGB unveiled agricultural zones associated with varying biomass throughout the cover crop development. Our findings underscored the complementarity of optical with SAR data to enhance AGB estimates of cover crops, offering valuable insights for agricultural zoning to support soil and cash crop management.

Assessing the Potential of Multi-Temporal Conditional Generative Adversarial Networks in SAR-to-Optical Image Translation for Early-Stage Crop Monitoring

The incomplete construction of optical image time series caused by cloud contamination is one of the major limitations facing the application of optical satellite images in crop monitoring. Thus, the construction of a complete optical image time series via image reconstruction of cloud-contaminated regions is essential for thematic mapping in croplands. This study investigates the potential of multi-temporal conditional generative adversarial networks (MTcGANs) that use a single synthetic aperture radar (SAR) image acquired on a prediction date and a pair of SAR and optical images acquired on a reference date in the context of early-stage crop monitoring. MTcGAN has an advantage over conventional SAR-to-optical image translation methods as it allows input data of various compositions. As the prediction performance of MTcGAN depends on the input data composition, the variations in the prediction performance should be assessed for different input data combination cases. Such an assessment was performed through experiments using Sentinel-1 and -2 images acquired in the US Corn Belt. MTcGAN outperformed existing SAR-to-optical image translation methods, including Pix2Pix and supervised CycleGAN (S-CycleGAN), in cases representing various input compositions. In particular, MTcGAN was substantially superior when there was little change in crop vitality between the reference and prediction dates. For the SWIR1 band, the root mean square error of MTcGAN (0.021) for corn was significantly improved by 54.4% and 50.0% compared to Pix2Pix (0.046) and S-CycleGAN (0.042), respectively. Even when there were large changes in crop vitality, the prediction accuracy of MTcGAN was more than twice that of Pix2Pix and S-CycleGAN. Without considering the temporal intervals between input image acquisition dates, MTcGAN was found to be beneficial when crops were visually distinct in both SAR and optical images. These experimental results demonstrate the potential of MTcGAN in SAR-to-optical image translation for crop monitoring during the early growth stage and can serve as a guideline for selecting appropriate input images for MTcGAN.

Six Decades of Changes in Pool Characteristics on a Concentric-Patterned Raised Bog

AbstractRaised bogs are wetland ecosystems which, under the right climatic conditions, feature patterns of pool hollows and hummock ridges. The relative cover and the spatial arrangement of pool and ridge microforms are thought to be influential on peatland atmosphere carbon gas fluxes and plant biodiversity. The mechanisms responsible for the formation and maintenance of pools, and the stability of these features in response to warming climates, remain topics of ongoing research. We employed historical aerial imagery, combined with a contemporary uncrewed aerial vehicle survey, to study 61 years of changes in pools at a patterned raised bog in central Sweden. We used a pool inheritance method to track individual pools between image acquisition dates throughout the time series. These data show a rapid loss of open-water pool area during the study period, primarily due to overgrowth of open-water pools by Sphagnum. We postulate that these changes are driven by ongoing climate warming that is accelerating Sphagnum colonisation. Open-water pool area declined by 26.8% during the study period, equivalent to a loss of 1001 m2 y−1 across the 150-hectare site. This is contradictory to an existing theory that states pools are highly stable, once formed, and can only convert to a terrestrial state through catastrophic drainage. The pool inheritance analysis shows that smaller pools are liable to become completely terrestrialised and expire. Our findings form part of a growing body of evidence for the loss of open-water habitats in peatlands across the boreal and elsewhere.

Coffee yield prediction using high-resolution satellite imagery and crop nutritional status in Southeast Brazil

Timely and accurate prediction of arabica coffee yield is pivotal to support harvest planning and to increase the profitability in the coffee industry. Currently, yield estimates are made by harvesting coffee fruits in a few plants on the field, whose actual yield is then extrapolated to the entire production area. These estimates are time-consuming and considered subjective, demonstrating the need for faster and more accurate methodologies to predict the coffee yield. Therefore, this study aimed to (1) compare the effectiveness of using spectral bands and VIs versus foliar nutrient content for yield prediction, as well as to (2) evaluate the feasibility of combining these variables as input for developing more robust prediction models. For that, an experiment was set up in a 22-ha commercial field of arabica coffee located in Southern Minas Gerais State, Brazil. Data collection was performed using a georeferenced regular grid with 64 sampling points (57 × 57 m). The spectral variables were composed of five bands (RGB, redEdge, and NIR) and six VIs derived from the RapidEye satellite imagery. Images from 10 dates were acquired throughout the 2011–2012 and 2012–2013 crop seasons. The foliar nutrient analyses were composed of nitrogen, phosphorus, potassium, calcium, and magnesium. Lastly, the coffee yield (60 kg-bag ha−1) was determined by manual harvesting of the coffee fruits in the five plants within each sampled point. The average value of the five plants was considered as the yield of the sampled point. Then, prediction models based on simple and multiple linear regression were developed using as input the results of a principal component analysis, which was carried out considering the dataset from each image acquisition date. Overall, the regression models based only on the spectral data enabled the prediction of the crop yield up to 9 months before the harvest date with R2 and RMSE values ranging from 0.04 to 0.69 and from 36.45 to 18.43 bags ha−1 for both seasons. In addition, when the foliar nutrient contents were combined with the spectral bands and VIs, the accuracy was improved with R2 and RMSE varying from 0.57 to 0.72 and from 23.78 to 19.39 bags ha−1. Finally, the study demonstrated that the time-consuming methodology can be replaced or supported by alternative approaches, especially, when using high-resolution satellite imagery.

Dam Surface Deformation Monitoring and Analysis Based on PS-InSAR Technology: A Case Study of Xiaolangdi Reservoir Dam in China

The Xiaolangdi Dam is a key project for the control and development of the Yellow River. It bears the functions of flood control, controlling water and sediment in the lower reaches, ice prevention, industrial and agricultural water supply, power generation, and so on. Its safety is related to people’s life and property safety and local economic and social development. It is of great significance to carry out comprehensive and regular deformation monitoring for dams since the deformation is an important evaluation index for dam safety. Interferometric Synthetic Aperture Radar (InSAR) technology has been a rapidly evolving technology in the field of space geodesy in recent years. It offers advantages such as high monitoring precision, extensive coverage, and high monitoring point density, making it a powerful tool for monitoring deformations in hydraulic engineering projects. Based on Sentinel-1 data covering the Xiaolangdi Dam from September 2020 to November 2022, the PS-InSAR technique was used to obtain the surface deformation of the Xiaolangdi Dam, and reservoir water level data on image acquisition dates were obtained for joint analysis. The results show that there is a large deformation in the center of the dam crest of the Xiaolangdi Dam, while both sides of the slope and downstream dam foot are relatively stable. The time series deformation of the dam body is closely related to the reservoir water level change. When the water level increases, the dam body tends to deform downstream; when the water level decreases, the dam body tends to deform upstream. The deformation and water level of the Xiaolangdi Dam exhibit a clear negative correlation. There is no significant cumulative deformation on the dam slopes or at the base of the dam. However, cumulative deformation occurs over time in the central area of the dam’s crest. The deformation process at the central area of the dam’s crest follows a continuous and non-disruptive pattern, which is consistent with the typical deformation behavior of the Xiaolangdi earth–rock dam structure. Therefore, it is judged that the current deformation of the Xiaolangdi Dam does not impact the safe operation of the dam. InSAR technology enables the rapid acquisition of high-precision, high-density deformation information on the surfaces of reservoir dams. With an increasing number of radar satellites in various frequency bands, such as Sentinel-1 and TerraSAR-X, there is now an ample supply of available data sources for InSAR applications. Consequently, InSAR technology can be extended to routine monitoring applications for reservoir dam deformations, especially for small and medium-sized reservoirs that may not be equipped with ground measurement tools like GNSS. This holds significant importance and potential for enhancing the safety monitoring of such reservoirs.

Preliminary Study on InSAR-Based Uplift or Subsidence Monitoring and Stability Evaluation of Ground Surface in the Permafrost Zone of the Qinghai–Tibet Engineering Corridor, China

Against the background of global warming, permafrost areas are facing increasing thawing, and the threat to the surface of the Qinghai–Tibet Engineering Corridor (QTEC) is serious. It is imperative to understand the current surface deformation and analyze the changes spatiotemporal characteristics for future warnings. At present, observation of a long time series and overall coverage of vertical ground deformation in QTEC are lacking. This paper takes the permafrost deformation of the QTEC as its research object. It uses the pretreated LiCSAR product and combines it with the LiCSBAS package to obtain monitoring results of the long time series deformation of the engineering corridor’s surface. The SAR image acquisition date is taken as the constraint, the results covering the whole processing area are selected, and then the vertical deformation information covering the entire engineering corridor area by ignoring the north–south displacement is calculated. The results show that the surface of the study area, as a whole, slightly subsided between May 2017 and March 2022, and the vertical deformation rate was mostly distributed at −27.068 mm/yr − 18.586 mm/yr, with an average of −1.06 mm/yr. Vertical deformation dominated at 52.84 percent of the study area, of which settlement accounted for 27.57 percent and uplift accounted for 25.27 percent. According to the statistics of the normal distribution of deformation velocity per pixel, a total of 77% of the engineering corridor was stable, with a vertical deformation rate between −6.964 mm/yr and −4.844 mm/yr, and 17.7% of the region was sub-stable, with a settling rate of −12.868 mm/yr − –6.964 mm/yr. The unstable regions included areas with settlement rates greater than 12.868 mm/yr and uplift rates greater than 10.748 mm/yr, representing 4.4 percent and 0.9 percent of the total area, respectively, for a total of 5.3 percent. The results of this paper can be used as the theoretical basis and as basic data for decision making and scientific research in various departments, and they are of great significance for surface stability assessment and early warnings along engineering corridors and traffic projects.

A CROSS-SENSOR-BASED APPROACH TO ESTIMATE DEPTH VALUES IN NEARSHORE COASTAL WATERS, CASE STUDY: NAYBAND BAY, PERSIAN GULF

Abstract. A cross-sensor-based approach using Landsat-8 OLI (L8/OLI) and Sentinel-2A MSI (S2A/MSI) imagers was examined to estimate bathymetric data in nearshore coastal waters. An L8/OLI image and an S2A/MSI image (Acquisition date: November 16, 2017) were selected from Nayband Bay, the southern region of Iran. In addition, precise bathymetric data for the studied area were used to calibrate the models and validate the results. Ratio together with traditional linear transform methods and a novel cross-sensor-based method were conducted to determine the depth values from both satellite images. Four bands of L8/OLI imager (Band No.1: Coastal/Aerosol [0.435–0.451 µm], Band No. 2: blue [0.452–0.512 µm], Band No. 3: green [0.533–0.590 µm], and Band No. 4: red [0.636–0.673 µm], spatial resolution: 30 m) were considered to create the aforementioned models while the three bands of S2A/ MSI imager were used (Band No. 2: blue [0.458–0.523 µm], Band No. 3: green [0.543-0.578 µm], and Band No. 4: red [0.650–0.680 µm], spatial resolution: 10 m). All models' accuracy was evaluated using comparing the calculated bathymetric information with field observed values. The statistical indicators including correlation coefficients (R2), root mean square errors (RMSE), and standard errors (SE) for validation points were computed for all models of two imagers. The final results demonstrated that although the spatial resolution of L8/OLI imagery is less than S2A/MSI, the precision of estimated depth is higher due to having more bands in the visible wavelength range. However, the integrated cross-sensor-based method including the bands of both sensors yielded the most accurate results (R2 = 0.90, RMSE = 1.66 m, and SE = 1.29 m).

Exploiting Sentinel-2 dataset to assess flow intermittency in non-perennial rivers

Knowledge about the frequency and duration of each flowing status of non-perennial rivers is severely limited by the small number of streamflow gauges and reliable prediction of surface water presence by hydrological models. In this study, multispectral Sentinel-2 images were used to detect and monitor changes in water surface presence along three non-perennial Mediterranean rivers located in southern Italy. Examining the reflectance values of water, sediment and vegetation covers, the bands in which these classes are most differentiated were identified. It emerged that the false-color composition of the Sentinel-2 bands SWIR, NIR and RED allows water surfaces to be clearly distinguished from the other components of the river corridor. From the false-color composite images, it was possible to identify the three distinct flowing status of non-perennial rivers: “flowing” (F), “ponding” (P) and “dry” (D). The results were compared with field data and very high-resolution images. The flowing status was identified for all archive images not affected by cloud cover. The obtained dataset allowed to train Random Forest (RF) models able to fill temporal gaps between satellite images, and predict the occurrence of one of the three flowing status (F/P/D) on a daily scale. The most important predictors of the RF models were the cumulative rainfall and air temperature data before the date of satellite image acquisition. The performances of RF models were very high, with total accuracy of 0.82–0.97 and true skill statistic of 0.64–0.95. The annual non-flowing period (phases P and D) of the monitored rivers was assessed in range 5 to 192 days depending on the river reach. Due to the easy-to-use algorithm and the global, freely available satellite imagery, this innovative technique has large application potential to describe flowing status of non-perennial rivers and estimate frequency and duration of surface water presence.

MUSTFN: A spatiotemporal fusion method for multi-scale and multi-sensor remote sensing images based on a convolutional neural network

• A deep learning spatiotemporal fusion method for large area remote sensing images. • Multi-constraint loss function to improve model accuracy. • Multi-scale features to avoid the influence of different sensor registration errors on fusion results. • Model is suitable for drastically changing remote sensing image fusion scenarios. • Model has strong transferability for remote sensing images at different times and locations. Spatiotemporal data fusion is a commonly-used and well-proven technique to enhance the application potential of multi-source remote sensing images. However, most existing methods have trouble in generating quality fusion results when areas covered by the images undergoes rapid land cover changes or images have substantial registration errors. While deep learning algorithms have demonstrated their capabilities for imagery fusion, it is challenging to apply deep-learning-based fusion methods in regions that experiences persistent cloud covers and have limited cloud-free imagery observations. To address these challenges, we developed a Multi-scene Spatiotemporal Fusion Network (MUSTFN) algorithm based on a Convolutional Neural Network (CNN). Our approach uses multi-level features to fuse images at different resolutions acquired by multiple sensors. Furthermore, MUSTFN uses the multi-scale features to overcome the effects of geometric registration errors between different images. Additionally, a multi-constrained loss function is proposed to improve the accuracy of imagery fusion over large areas and solve fusion and gap-filling problems simultaneously by utilizing cloud-contaminated images with the fine-tuning method. Compared with several commonly-used methods, our proposed MUSTFN performs better in fusing the 30-m Landsat-7 images and 500-m MODIS images over a small area that has undergone large changes (the average relative Mean Absolute Errors (rMAE) of the first four bands are 6.8% by MUSTFN as compared to 14.1% by the Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM), 12.8% by the Flexible Spatiotemporal Data Fusion (FSDAF), 8.4% by the Extended Super-Resolution Convolutional Neural Network (ESRCNN), 8.1% by the Spatiotemporal Fusion Using a Generative Adversarial Network (STFGAN)). In particularly for images at different resolutions with different registration accuracies (e.g., 16-m Chinese GaoFen-1 and 500-m MODIS), MUSTFN achieved fusion results of good quality with an average rMAE of 9.3% in spectral reflectance at the first four bands. Finally, we demonstrated the applicability of MUSTFN (average rMAE of 9.18%) when fusing long-term Landsat-8 composite images and MODIS images over a large region (830 km × 600 km). Overall, our results suggest the effectiveness of MUSTFN to address the challenges in imagery fusion, including rapid land cover changes between image acquisition dates, geometric misregistration between images and limited availabilities of cloud-free images. The program of MUSTFN is freely available at: https://github.com/qpyeah/MUSTFN .

Effectiveness of the Reconstructed MODIS Typical-Angle Reflectances on Forest Biomass Estimation

Multi-angle optical reflectance measurements such as those from the NASA moderate resolution imaging spectroradiometer (MODIS) are sensitive to forest 3D structures, potentially serving as a useful proxy to estimate forest structural variables such as aboveground biomass (AGB)—a potential theoretically recognized but rarely explored. In this paper, we examined the effectiveness of the reconstructed MODIS typical-angle reflectances—reflectances observed from the hotspot, darkspot, and nadir directions—for estimating forest AGB from both theoretical and practical perspectives. To gain theoretical insights, we first tested the sensitivities of typical-angle reflectances to forest AGB through simulations using the 4-scale bidirectional reflectance distribution function (BRDF) model. We then built statistical models to fit the relationship between MODIS multi-angle observations and field-measured deciduous-broadleaf/mixed-temperate forest AGB at five sites in the eastern USA, assisted by a semivariogram analysis to determine the effect of pixel heterogeneity on the MODIS–AGB relationship. We also determined the effects of terrain and season on the predictive relationships. Our results indicated that multi-angle reflectances with fewer visible shadows yielded better AGB estimates (hotspot: R2 = 0.63, RMSE = 54.28 Mg/ha; nadir: R2 = 0.55, RMSE = 59.95 Mg/ha; darkspot: R2 = 0.46, RMSE = 65.66 Mg/ha) after filtering out the effects of complex terrain and pixel heterogeneity; the MODIS typical-angle reflectances in the NIR band were the most sensitive to forest AGB. We also found strong sensitivities of estimated accuracies to MODIS image acquisition dates or season. Overall, our results suggest that the current practice of leveraging only single-angle MODIS data can be a suboptimal strategy for AGB estimation. We advocate the use of MODIS multi-angle reflectances for optical remote sensing of forest AGB or potentially other ecological applications requiring forest structure information.

Ecological quality assessment and monitoring using a time-series remote sensing-based ecological index (ts-RSEI)

ABSTRACT Ecological quality assessment is fundamental to revealing changes in ecological environments before the development of effective ecological conservation policies. The complex ecological environment can be assessed more reliably when multiple remote sensing indices are integrated, such as in the use of the prevalent Remote Sensing-based Ecological Index (RSEI). However, for effective ecological quality assessment, the requirement of acquisition time consistency for images has become an outstanding issue for broadening the application of the RSEI. In this study, we adjusted the RSEI to the Continuous Change Detection and Classification (CCDC) algorithm that predicts synthetic images instead of real images. Based on this algorithm, we mapped time-series RSEI (ts-RSEI), which provide comparable results for tracing the dynamics of ecological quality at any time. Our major findings are as follows: (1) The RSEI is very sensitive to the timespan of the image acquisition dates, with the Mean Absolute Difference (MAD) of 0.111 (19.2%) when the interval between dates exceeds one month. (2) The ts-RSEI from synthetic images is comparable to the RSEI from real images, with the MAD of 0.075 (10.5%), which is superior to that of two real images with the timespan of half-a-month. (3) For Hangzhou, the ecological quality was maintained for almost the past 35 years (the ts-RSEI changed from 0.679 to 0.705). However, special attention should be paid to the spatial polarization between natural (“better”) and human-dominated (“worse”) environments. The high temporal consistency and the capability of any- time mapping of the ts-RSEI are expected to be of value to policy makers and authorities in implementing effective ecological conservation measures.

Temporal Sequence Object-based CNN (TS-OCNN) for crop classification from fine resolution remote sensing image time-series

Accurate crop distribution mapping is required for crop yield prediction and field management. Due to rapid progress in remote sensing technology, fine spatial resolution (FSR) remotely sensed imagery now offers great opportunities for mapping crop types in great detail. However, within-class variance can hamper attempts to discriminate crop classes at fine resolutions. Multi-temporal FSR remotely sensed imagery provides a means of increasing crop classification from FSR imagery, although current methods do not exploit the available information fully. In this research, a novel Temporal Sequence Object-based Convolutional Neural Network (TS-OCNN) was proposed to classify agricultural crop type from FSR image time-series. An object-based CNN (OCNN) model was adopted in the TS-OCNN to classify images at the object level (i.e., segmented objects or crop parcels), thus, maintaining the precise boundary information of crop parcels. The combination of image time-series was first utilized as the input to the OCNN model to produce an ‘original’ or baseline classification. Then the single-date images were fed automatically into the deep learning model scene-by-scene in order of image acquisition date to increase successively the crop classification accuracy. By doing so, the joint information in the FSR multi-temporal observations and the unique individual information from the single-date images were exploited comprehensively for crop classification. The effectiveness of the proposed approach was investigated using multitemporal SAR and optical imagery, respectively, over two heterogeneous agricultural areas. The experimental results demonstrated that the newly proposed TS-OCNN approach consistently increased crop classification accuracy, and achieved the greatest accuracies (82.68% and 87.40%) in comparison with state-of-the-art benchmark methods, including the object-based CNN (OCNN) (81.63% and 85.88%), object-based image analysis (OBIA) (78.21% and 84.83%), and standard pixel-wise CNN (79.18% and 82.90%). The proposed approach is the first known attempt to explore simultaneously the joint information from image time-series with the unique information from single-date images for crop classification using a deep learning framework. The TS-OCNN, therefore, represents a new approach for agricultural landscape classification from multi-temporal FSR imagery. Besides, it is readily generalizable to other landscapes (e.g., forest landscapes), with a wide application prospect.

The effects of Landsat image acquisition date on winter wheat classification in the North China Plain

Accurate winter wheat distribution provides critical information for yield estimation and agricultural resources monitoring, which is associated with food security and agricultural ecosystem sustainability. The increasingly high spatiotemporal resolutions of globally available satellite images (e.g., Landsat) create new possibilities for generating accurate datasets. Although winter wheat classification using Landsat time-series data has been increasingly acknowledged in the literature, the contributing effects of a single acquisition date on classification remain poorly explored. Accordingly, this study aimed to evaluate the effects of a single acquisition date (nine acquisition dates were obtained throughout the growing season) on winter wheat classification using multi-temporal Landsat 8 imagery. We adopted Dynamic time warping (DTW) to discriminate winter wheat and determined the most relevant acquisition dates for classification accuracy with different numbers of images. The most significant advantage of DTW from other similarity measurement methods is that DTW can identify the optimal alignment of two time-series datasets with an unequal number of images. Then, we calculated the importance of each acquisition date using the random forest algorithm and quantified their contributions to the classification using variance analysis. The conditional combination of our best accuracy was 84.51% for overall accuracy (OA) and 84.62% for F-score when all nine images were used for the classification. While the lowest accuracy was 46.2% for OA and 51.3% for F-score through the classification of two image combinations from the wintering and heading images. It was shown that the initial and late growth images were the most discriminating dates for time series classification of winter wheat in ∼ 91% of the total combinations explored (i.e., 456 combinations). The main effects of the late growth images and their interactions significantly affected model accuracy, while the interactions between the initial growth images also played an important role, particularly for greater numbers of acquisition dates. The relative contributions explained by the main effects of late growth images gradually decreased with the increasing image acquisition dates, while those explained by the internal interactions of both initial and late growth images significantly increased. The wide distribution of winter wheat in many parts of the world and its strong consequences for global food security suggest that better monitoring of wheat is necessary, and the results indicated that appropriate selection of image dates was significant for accomplishing this task.

Multiscale framework for rapid change analysis from SAR image time series: Case study of flood monitoring in the central coast regions of Vietnam

Recently, the frequency of natural and environmental disasters has increased significantly, causing constant changes on the Earth's surface. Synthetic Aperture Radar (SAR) data have been proved to be useful for operational change monitoring tasks. The multiscale framework presented in this paper aims at detecting and analyzing changes using SAR image time series composed of large-size images. Spatio-temporal changes are initially detected at the subimage scale analysis stage to determine regions and image acquisition dates related to the change occurrence. Detailed changes are then identified at the pixel scale analysis stage between selected acquisitions at each recognized region. This framework was used for flood monitoring over a large area along the central coast of Vietnam (from Thua Thien Hue province to Quang Nam province). We exploited a Sentinel-1 image time series acquired during two rainy seasons and typhoon seasons in the Western Pacific (from September to December of the two years 2017 and 2018). The proposed framework detected flooded areas with a high overall accuracy of 90.4% and could analyze different types of changes that occurred in this time series, i.e. dirac, periodic, chaotic changes, and temporal stability.

THE CONTRIBUTION OF REMOTE SENSING AND AEROMAGNETISM TO GOLD PROSPECTING: THE CASE OF THE MEIGANGA ZONE, CAMEROON

In order to optimize gold prospecting in the Meiganga zone located in the Adamaoua region of Cameroon, aeromagnetic and remote sensing prospecting was carried out in the eastern and southern parts. The remote sensing approach on a Landsat 8 OLI/TIRS image highlighted areas of maximum gold concentration. Thus, ferric ion bearing minerals are located in the North-West, silicate minerals bearing ferrous ions are in the Centre while clay minerals are in the North-East and East. The principal component analysis revealed important structural information. The PCA Spatial Map (PC1, PC2, PC3) showed the plutonic formations composed of anatexis and anatexis granites, vegetation cover (at the date of image acquisition: February 22, 2019), areas of permanent water circulation or accumulation, and metamorphic and sedimentary formations namely gneisses, quartzites, schists and superficial clay formations. A Landsat SRTM (Shuttle Radar Topography Mission) image was also used to enhance the lineaments through the Sobel filter to highlight the geomorphological (cliffs, valleys, ...) and topographic (river network, ridge and drainage segment) structures. The aeromagnetic approach was also important. The study of the modified magnetic field (CM) showed 4 ranges: very high, high, medium and low. The Total Magnetic Anomalies (TMI) of the area are subdivided into 2 ranges large positive anomalies (221.1-103.0 nT) located in the lower part of NE-SW orientation, small positive anomalies (103.0-(-)89.7 nT) located in the upper part of NE-SW orientation. The reduced total magnetic anomaly at the equator shows a fairly similar distribution to the total magnetic anomaly with the large positive anomalies in almost the entire lower part. Superimposed on the geological map, Neoproterozoic pre- to syn-tectonic granitoids (C) are superimposed on the large positive anomalies and Neoproterozoic conglomerates, quartzites, sedimentary shales and volcanosedimentary rocks (A) and Neoproterozoic syn-tectonic granitoids (B) are superimposed on the large and small positive anomalies. The grid of the reduced residual equatorial anomaly (ARRE) confirms that the local geology is strongly magnetic (gneiss and quartzite). The filters of the derivatives allowed to establish a map of magnetic lineaments of major orientation N045° and minor orientation N130°. The horizontal gadient superimposed on the local maxima showed the presence of deep structures oriented NE-SW. The analytical signal superimposed on the local maxima highlights the metamorphic basement consisting of rocks with strong magnetism. The application of Euler deconvolution localizes the depth of the sources of linear anomalies.

A Sentinel-2 Image-Based Irrigation Advisory Service: Cases for Tea Plantations

In this study, we aim to develop an inexpensive site-specific irrigation advisory service for resolving disadvantages related to using immobile soil moisture sensors and to the differences in irrigation needs of different tea plantations affected by variabilities in cultivars, plant ages, soil heterogeneity, and management practices. In the paper, we present methodologies to retrieve two biophysical variables, surface soil water content and canopy water content of tea trees from Sentinel-2 (S2) (European Space Agency, Paris, France) images and consider their association with crop water availability status to be used for making decisions to send an alert level. Precipitation records are used as auxiliary information to assist in determining or modifying the alert level. Once the site-specific alert level for each target plantation is determined, it is sent to the corresponding farmer through text messaging. All the processes that make up the service, from downloading an S2 image from the web to alert level text messaging, are automated and can be completed before 7:30 a.m. the next day after an S2 image was taken. Therefore, the service is operated cyclically, and corresponds to the five-day revisit period of S2, but one day behind the S2 image acquisition date. However, it should be noted that the amount of irrigation water required for each site-specific plantation has not yet been estimated because of the complexities involved. Instead, a single irrigation rate (300 t ha−1) per irrigation event is recommended. The service is now available to over 20 tea plantations in the Mingjian Township, the largest tea producing region in Taiwan, free of charge since September 2020. This operational application is expected to save expenditures on buying irrigation water and induce deeper root systems by decreasing the frequency of insufficient irrigation commonly employed by local farmers.

Development of a Prognostic AI-Monitor for Metastatic Urothelial Cancer Patients Receiving Immunotherapy

Background: Immune checkpoint inhibitor efficacy in advanced cancer patients remains difficult to predict. Imaging is the only technique available that can non-invasively provide whole body information of a patient's response to treatment. We hypothesize that quantitative whole-body prognostic information can be extracted by leveraging artificial intelligence (AI) for treatment monitoring, superior and complementary to the current response evaluation methods.Methods: To test this, a cohort of 74 stage-IV urothelial cancer patients (37 in the discovery set, 37 in the independent test, 1087 CTs), who received anti-PD1 or anti-PDL1 were retrospectively collected. We designed an AI system [named prognostic AI-monitor (PAM)] able to identify morphological changes in chest and abdominal CT scans acquired during follow-up, and link them to survival.Results: Our findings showed significant performance of PAM in the independent test set to predict 1-year overall survival from the date of image acquisition, with an average area under the curve (AUC) of 0.73 (p < 0.001) for abdominal imaging, and 0.67 AUC (p < 0.001) for chest imaging. Subanalysis revealed higher accuracy of abdominal imaging around and in the first 6 months of treatment, reaching an AUC of 0.82 (p < 0.001). Similar accuracy was found by chest imaging, 5–11 months after start of treatment. Univariate comparison with current monitoring methods (laboratory results and radiological assessments) revealed higher or similar prognostic performance. In multivariate analysis, PAM remained significant against all other methods (p < 0.001), suggesting its complementary value in current clinical settings.Conclusions: Our study demonstrates that a comprehensive AI-based method such as PAM, can provide prognostic information in advanced urothelial cancer patients receiving immunotherapy, leveraging morphological changes not only in tumor lesions, but also tumor spread, and side-effects. Further investigations should focus beyond anatomical imaging. Prospective studies are warranted to test and validate our findings.

Using Unmanned Aerial Vehicle and Ground-Based RGB Indices to Assess Agronomic Performance of Wheat Landraces and Cultivars in a Mediterranean-Type Environment

The adaptability and stability of new bread wheat cultivars that can be successfully grown in rainfed conditions are of paramount importance. Plant improvement can be boosted using effective high-throughput phenotyping tools in dry areas of the Mediterranean basin, where drought and heat stress are expected to increase yield instability. Remote sensing has been of growing interest in breeding programs since it is a cost-effective technology useful for assessing the canopy structure as well as the physiological traits of large genotype collections. The purpose of this study was to evaluate the use of a 4-band multispectral camera on-board an unmanned aerial vehicle (UAV) and ground-based RGB imagery to predict agronomic traits as well as quantify the best estimation of leaf area index (LAI) in rainfed conditions. A collection of 365 bread wheat genotypes, including 181 Mediterranean landraces and 184 modern cultivars, was evaluated during two consecutive growing seasons. Several vegetation indices (VI) derived from multispectral UAV and ground-based RGB images were calculated at different image acquisition dates of the crop cycle. The modified triangular vegetation index (MTVI2) proved to have a good accuracy to estimate LAI (R2 = 0.61). Although the stepwise multiple regression analysis showed that grain yield and number of grains per square meter (NGm2) were the agronomic traits most suitable to be predicted, the R2 were low due to field trials were conducted under rainfed conditions. Moreover, the prediction of agronomic traits was slightly better with ground-based RGB VI rather than with UAV multispectral VIs. NDVI and GNDVI, from multispectral images, were present in most of the prediction equations. Repeated measurements confirmed that the ability of VIs to predict yield depends on the range of phenotypic data. The current study highlights the potential use of VI and RGB images as an efficient tool for high-throughput phenotyping under rainfed Mediterranean conditions.

Prognostic Value of Deep Learning-Mediated Treatment Monitoring in Lung Cancer Patients Receiving Immunotherapy.

BackgroundCheckpoint inhibitors provided sustained clinical benefit to metastatic lung cancer patients. Nonetheless, prognostic markers in metastatic settings are still under research. Imaging offers distinctive advantages, providing whole-body information non-invasively, while routinely available in most clinics. We hypothesized that more prognostic information can be extracted by employing artificial intelligence (AI) for treatment monitoring, superior to 2D tumor growth criteria.MethodsA cohort of 152 stage-IV non-small-cell lung cancer patients (NSCLC) (73 discovery, 79 test, 903CTs), who received nivolumab were retrospectively collected. We trained a neural network to identify morphological changes on chest CT acquired during patients’ follow-ups. A classifier was employed to link imaging features learned by the network with overall survival.ResultsOur results showed significant performance in the independent test set to predict 1-year overall survival from the date of image acquisition, with an average area under the curve (AUC) of 0.69 (p < 0.01), up to AUC 0.75 (p < 0.01) in the first 3 to 5 months of treatment, and 0.67 AUC (p = 0.01) for durable clinical benefit (6 months progression-free survival). We found the AI-derived survival score to be independent of clinical, radiological, PDL1, and histopathological factors. Visual analysis of AI-generated prognostic heatmaps revealed relative prognostic importance of morphological nodal changes in the mediastinum, supraclavicular, and hilar regions, lung and bone metastases, as well as pleural effusions, atelectasis, and consolidations.ConclusionsOur results demonstrate that deep learning can quantify tumor- and non–tumor-related morphological changes important for prognostication on serial imaging. Further investigation should focus on the implementation of this technique beyond thoracic imaging.