Current hyperspectral image classification assumes that a predefined classification system is closed and complete, and there are no unknown or novel classes in the unseen data. However, this assumption may be too strict for the real world. Often, novel classes are overlooked when the classification system is constructed. The closed nature forces a model to assign a label given a new sample and may lead to overestimation of known land covers (e.g., crop area). To tackle this issue, we propose a multitask deep learning method that simultaneously conducts classification and reconstruction in the open world (named MDL4OW) where unknown classes may exist. The reconstructed data are compared with the original data; those failing to be reconstructed are considered unknown based on the assumption that they are not well represented in the latent features due to the lack of labels. A threshold needs to be defined to separate the unknown and known classes; we propose two strategies based on the extreme value theory for few- and many-shot scenarios. The proposed method was tested on real-world hyperspectral images; state-of-the-art results were achieved, e.g., improving the overall accuracy by 4.94% for the Salinas data. By considering the existence of unknown classes in the open world, our method achieved more accurate hyperspectral image classification, especially under the few-shot context.

Object-based image analysis (OBIA) has been widely used for land use and land cover (LULC) mapping using optical and synthetic aperture radar (SAR) images because it can utilize spatial information, reduce the effect of salt and pepper, and delineate LULC boundaries. With recent advances in machine learning, convolutional neural networks (CNNs) have become state-of-the-art algorithms. However, CNNs cannot be easily integrated with OBIA because the processing unit of CNNs is a rectangular image, whereas that of OBIA is an irregular image object. To obtain object-based thematic maps, this study developed a new method that integrates object-based post-classification refinement (OBPR) and CNNs for LULC mapping using Sentinel optical and SAR data. After producing the classification map by CNN, each image object was labeled with the most frequent land cover category of its pixels. The proposed method was tested on the optical-SAR Sentinel Guangzhou dataset with 10 m spatial resolution, the optical-SAR Zhuhai-Macau local climate zones (LCZ) dataset with 100 m spatial resolution, and a hyperspectral benchmark the University of Pavia with 1.3 m spatial resolution. It outperformed OBIA support vector machine (SVM) and random forest (RF). SVM and RF could benefit more from the combined use of optical and SAR data compared with CNN, whereas spatial information learned by CNN was very effective for classification. With the ability to extract spatial features and maintain object boundaries, the proposed method considerably improved the classification accuracy of urban ground targets. It achieved overall accuracy (OA) of 95.33% for the Sentinel Guangzhou dataset, OA of 77.64% for the Zhuhai-Macau LCZ dataset, and OA of 95.70% for the University of Pavia dataset with only 10 labeled samples per class.

In this letter, we propose a multitask deep learning method for the classification of multiple hyperspectral data in a single training. Deep learning models have achieved promising results on hyperspectral image classification, but their performance highly relies on sufficient labeled samples that are scarce on hyperspectral images. However, samples from multiple data sets might be sufficient to train one deep learning model, thereby improving its performance. To do so, we trained an identical feature extractor for all data, and the extracted features were fed into corresponding softmax classifiers. Spectral knowledge was introduced to ensure that the shared features were similar across domains. Four hyperspectral data sets were used in the experiments. We achieved higher classification accuracies on three data sets (Pavia University, Pavia Center, and Indian Pines) and competitive results on the Salinas Valley data compared with the baseline. Spectral knowledge was useful to prevent the deep network from overfitting when the data shared similar spectral response. The proposed method tested on two deep CNNs successfully shows its ability to utilize samples from multiple data sets and to enhance networks' performance.

Although deep learning has achieved great success in the image-classification tasks, its performance is subject to the quantity and quality of the training samples. For the classification of the polarimetric synthetic aperture radar (PolSAR) images, it is nearly impossible to annotate the images from visual interpretation. Therefore, it is urgent for remote-sensing scientists to develop new techniques for PolSAR image classification under the condition of very few training samples. In this letter, we take the advantage of active learning and propose active ensemble deep learning (AEDL) for PolSAR image classification. We first show that only 35% of the predicted labels of the deep-learning model's snapshots near its convergence were exactly the same. The disagreement between the snapshots is nonnegligible. From the perspective of multiview learning, the snapshots together serve as a good committee to evaluate the importance of the unlabeled instances. Using the snapshot committee to give out the informativeness of the unlabeled data, the proposed AEDL achieved better performance on two real PolSAR images than the standard active learning strategies. It achieved the same classification accuracy with only 86% and 55% of the training samples compared to the breaking tie active learning and random selection for the Flevoland data set.

Many real-world applications rely on land surface temperature (LST) data at high spatiotemporal resolution. In complex urban areas, LST exhibits significant variations, fluctuating dramatically within and across city blocks. Landsat provides high spatial resolution data at 100 meters but is limited by long revisit time, with cloud cover further disrupting data collection. Here, we propose DELAG, a deep ensemble learning method that integrates annual temperature cycles and Gaussian processes, to reconstruct Landsat LST in complex urban areas. Leveraging the cross-track characteristics and dual-satellite operation of Landsat since 2021, we further enhance data availability to 4 scenes every 16 days. We select New York City, London and Hong Kong from three different continents as study areas. Experiments show that DELAG successfully reconstructed LST in the three cities under clear-sky (RMSE = 0.73-0.96 K) and heavily-cloudy (RMSE = 0.84-1.62 K) situations, superior to existing methods. Additionally, DELAG can quantify uncertainty that enhances LST reconstruction reliability. We further tested the reconstructed LST to estimate near-surface air temperature, achieving results (RMSE = 1.48-2.11 K) comparable to those derived from clear-sky LST (RMSE = 1.63-2.02 K). The results demonstrate the successful reconstruction through DELAG and highlight the broader applications of LST reconstruction for estimating accurate air temperature. Our study thus provides a novel and practical method for Landsat LST reconstruction, particularly suited for complex urban areas within Landsat cross-track areas, taking one step toward addressing complex climate events at high spatiotemporal resolution. Code and data will be available at skrisliu.com/delag.