Cloud detection in remote sensing images is a challenging but significant task. Due to the variety and complexity of underlying surfaces, most of the current cloud detection methods have difficulty in detecting thin cloud regions. In fact, it is quite meaningful to distinguish thin clouds from thick clouds, especially in cloud removal and target detection tasks. Therefore, we propose a method based on multiscale features-convolutional neural network (MF-CNN) to detect thin cloud, thick cloud, and noncloud pixels of remote sensing images simultaneously. Landsat 8 satellite imagery with various levels of cloud coverage is used to demonstrate the effectiveness of our proposed MF-CNN model. We first stack visible, near-infrared, short-wave, cirrus, and thermal infrared bands of Landsat 8 imagery to obtain the combined spectral information. The MF-CNN model is then used to learn the multiscale global features of input images. The high-level semantic information obtained in the process of feature learning is integrated with low-level spatial information to classify the imagery into thick, thin and noncloud regions. The performance of our proposed model is compared to that of various commonly used cloud detection methods in both qualitative and quantitative aspects. Compared to other cloud detection methods, the experimental results show that our proposed method has a better performance not only in thick and thin clouds but also in the entire cloud regions.
Dense time-series remote sensing data with detailed spatial information are highly desired for the monitoring of dynamic earth systems. Due to the sensor tradeoff, most remote sensing systems cannot provide images with both high spatial and temporal resolutions. Spatiotemporal image fusion models provide a feasible solution to generate such a type of satellite imagery, yet existing fusion methods are limited in predicting rapid and/or transient phenological changes. Additionally, a systematic approach to assessing and understanding how varying levels of temporal phenological changes affect fusion results is lacking in spatiotemporal fusion research. The objective of this study is to develop an innovative hybrid deep learning model that can effectively and robustly fuse the satellite imagery of various spatial and temporal resolutions. The proposed model integrates two types of network models: super-resolution convolutional neural network (SRCNN) and long short-term memory (LSTM). SRCNN can enhance the coarse images by restoring degraded spatial details, while LSTM can learn and extract the temporal changing patterns from the time-series images. To systematically assess the effects of varying levels of phenological changes, we identify image phenological transition dates and design three temporal phenological change scenarios representing rapid, moderate, and minimal phenological changes. The hybrid deep learning model, alongside three benchmark fusion models, is assessed in different scenarios of phenological changes. Results indicate the hybrid deep learning model yields significantly better results when rapid or moderate phenological changes are present. It holds great potential in generating high-quality time-series datasets of both high spatial and temporal resolutions, which can further benefit terrestrial system dynamic studies. The innovative approach to understanding phenological changes’ effect will help us better comprehend the strengths and weaknesses of current and future fusion models.
16 January 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Crop-type mapping using time-series remote sensing data is crucial for a wide range of agricultural applications. Crop mapping during the growing season is particularly critical in timely monitoring of the agricultural system. Most existing studies focusing on within-season crop mapping leverage historical remote sensing and crop type reference data for model building, due to the difficulty in obtaining timely crop type samples for the current growing season. Yet the crop type samples from previous years may not be used directly considering the diverse patterns of crop phenology across years and locations, which hampers the scalability and transferability of the model to the current season for timely crop mapping. This study proposes an innovative within-season emergence (WISE)-phenology normalized deep learning model towards scalable within-season crop mapping. The crop time-series remote sensing data are first normalized by the WISE crop emergence dates before being fed into an attention-based one-dimensional convolutional neural network (At1DCNN) classifier. Compared to conventional calendar-based approaches, the WISE-phenology normalization approach substantially helps the deep learning crop mapping model accommodate the spatiotemporal variations in crop phenological dynamics. Results in Illinois from 2017 to 2020 indicate that the proposed model outperforms calendar-based approaches and yields over 90% overall accuracy for classifying corn and soybeans at the end of season. During the growing season, the proposed model can give satisfactory performance (85% overall accuracy) one to four weeks earlier than calendar-based approaches. With WISE-phenology normalization, the proposed model exhibits more stable performance across Illinois and can be transferred to different years with enhanced scalability and robustness.
Detecting crop phenology with satellite time series is important to characterize agroecosystem energy-water-carbon fluxes, manage farming practices, and predict crop yields. Despite the advances in satellite-based crop phenological retrievals, interpreting those retrieval characteristics in the context of on-the-ground crop phenological events remains a long-standing hurdle. Over the recent years, the emergence of near-surface phenology cameras (e.g., PhenoCams), along with the satellite imagery of both high spatial and temporal resolutions (e.g., PlanetScope imagery), has largely facilitated direct comparisons of retrieved characteristics to visually observed crop stages for phenological interpretation and validation. The goal of this study is to systematically assess near-surface PhenoCams and high-resolution PlanetScope time series in reconciling sensor- and ground-based crop phenological characterizations. With two critical crop stages (i.e., crop emergence and maturity stages) as an example, we retrieved diverse phenological characteristics from both PhenoCam and PlanetScope imagery for a range of agricultural sites across the United States. The results showed that the curvature-based Greenup and Gu-based Upturn estimates showed good congruence with the visually observed crop emergence stage (RMSE about 1 week, bias about 0–9 days, and R square about 0.65–0.75). The threshold- and derivative-based End of greenness falling Season (i.e., EOS) estimates reconciled well with visual crop maturity observations (RMSE about 5–10 days, bias about 0–8 days, and R square about 0.6–0.75). The concordance among PlanetScope, PhenoCam, and visual phenology demonstrated the potential to interpret the fine-scale sensor-derived phenological characteristics in the context of physiologically well-characterized crop phenological events, which paved the way to develop formal protocols for bridging ground-satellite phenological characterization.
6 October 2023 in ISPRS Journal of Photogrammetry and Remote Sensing