Search

New satellite remote sensing and machine learning techniques offer untapped possibilities to monitor global biodiversity with unprecedented speed and precision. These efficiencies promise to reveal novel ecological insights at spatial scales which are germane to the management of populations and entire ecosystems. Here, we present a robust transferable deep learning pipeline to automatically locate and count large herds of migratory ungulates (wildebeest and zebra) in the Serengeti-Mara ecosystem using fine-resolution (38-50 cm) satellite imagery. The results achieve accurate detection of nearly 500,000 individuals across thousands of square kilometers and multiple habitat types, with an overall F1-score of 84.75% (Precision: 87.85%, Recall: 81.86%). This research demonstrates the capability of satellite remote sensing and machine learning techniques to automatically and accurately count very large populations of terrestrial mammals across a highly heterogeneous landscape. We also discuss the potential for satellite-derived species detections to advance basic understanding of animal behavior and ecology., (© 2023. The Author(s).)

Large-scale (large-area), fine spatial resolution satellite sensor images are valuable data sources for Earth observation while not yet fully exploited by research communities for practical applications. Often, such images exhibit highly complex geometrical structures and spatial patterns, and distinctive characteristics of multiple land-use categories may appear at the same region. Autonomous information extraction from these images is essential in the field of pattern recognition within remote sensing, but this task is extremely challenging due to the spectral and spatial complexity captured in satellite sensor imagery. In this research, a semi-supervised deep rule-based approach for satellite sensor image analysis (SeRBIA) is proposed, where large-scale satellite sensor images are analysed autonomously and classified into detailed land-use categories. Using an ensemble feature descriptor derived from pre-trained AlexNet and VGG-VD-16 models, SeRBIA is capable of learning continuously from both labelled and unlabelled images through self-adaptation without human involvement or intervention. Extensive numerical experiments were conducted on both benchmark datasets and real-world satellite sensor images to comprehensively test the validity and effectiveness of the proposed method. The novel information mining technique developed here can be applied to analyse large-scale satellite sensor images with high accuracy and interpretability, across a wide range of real-world applications. [ABSTRACT FROM AUTHOR]

• A novel semi-supervised ensemble framework with a cross-checking mechanism is proposed for remote sensing scene classification; • An enhanced self-training hierarchical prototype-based classifier is introduced as the base learner; • A novel pseudo-labelling mechanism is proposed to utilise the multi-granular information mined from data in decision-making; • The proposed ensemble framework can achieve top performance with a reduced requirement for labelled images. Remote sensing scene classification plays a critical role in a wide range of real-world applications. Technically, however, scene classification is an extremely challenging task due to the huge complexity in remotely sensed scenes, and the difficulty in acquiring labelled data for model training such as supervised deep learning. To tackle these issues, a novel semi-supervised ensemble framework is proposed here using the self-training hierarchical prototype-based classifier as the base learner for chunk-by-chunk prediction. The framework has the ability to build a powerful ensemble model from both labelled and unlabelled images with minimum supervision. Different feature descriptors are employed in the proposed ensemble framework to offer multiple independent views of images. Thus, the diversity of base learners is guaranteed for ensemble classification. To further increase the overall accuracy, a novel cross-checking strategy was introduced to enable the base learners to exchange pseudo-labelling information during the self-training process, and maximize the correctness of pseudo-labels assigned to unlabelled images. Extensive numerical experiments on popular benchmark remote sensing scenes demonstrated the effectiveness of the proposed ensemble framework, especially where the number of labelled images available is limited. For example, the classification accuracy achieved on the OPTIMAL-31, PatternNet and RSI-CB256 datasets was up to 99.91%, 98. 67% and 99.07% with only 40% of the image sets used as labelled training images, surpassing or at least on par with mainstream benchmark approaches trained with double the number of labelled images. [ABSTRACT FROM AUTHOR]

Future intelligent machines will be more human-friendly and human-like, while offering much higher throughput and automation, thus augmenting our (human) capabilities. Anthropomorphic machine learning is an emerging direction for future development in artificial intelligence (AI) and data science. This revolutionary shift offers human-like abilities to the next generation of machine learning with greater potential for underpinning breakthroughs in technology development as well as in various aspects of everyday life. [ABSTRACT FROM AUTHOR]

Pioneering the traditional fuzzy rule-based (FRB) systems, deep rule-based (DRB) classifiers are able to offer both human-level performance and transparent system structure on image classification problems by integrating zero-order fuzzy rule base with a multi-layer image-processing architecture that is typical for deep learning. Nonetheless, it is frequently observed that the inner structure of DRB can become over sophisticated and not interpretable for humans when applied to large-scale, complex problems. To tackle the issue, one feasible solution is to construct a tree structural classification model by aggregating the possibly huge number of prototypes identified from data into a much smaller number of more descriptive and highly abstract ones. Therefore, in this paper, we present a novel hierarchical deep rule-based (H-DRB) approach that is capable of summarizing the less descriptive raw prototypes into highly generalized ones and self-arranging them into a hierarchical prototype-based structure according to their descriptive abilities. By doing so, H-DRB can offer high-level performance and, most importantly, full transparency and human-interpretability on various problems including large-scale ones. The proposed concept and generical principles are verified through numerical experiments based on a wide variety of popular benchmark image sets. Numerical results demonstrate that the promise of H-DRB. • A generic approach for deep rule-based systems to self-organize a multi-layer structure is proposed. • The proposed system can offer higher transparency and human-interpretability for large-scale, complex problems. • The proposed approach can perform highly efficient decision-making with attractive classification precision. • The effectiveness and validity of the proposed approach are demonstrated on a variety of popular benchmark image sets. [ABSTRACT FROM AUTHOR]

• A multiscale superpixel reconstruction method was developed to generate the Difference Image. • A two-stage center-constrained FCM algorithm was designed to deal with imbalanced data clustering. • CWNN combined with DCGAN was adopted to classify hard pixels. Small area change detection using synthetic aperture radar (SAR) imagery is a highly challenging task, due to speckle noise and imbalance between classes (changed and unchanged). In this paper, a robust unsupervised approach is proposed for small area change detection using deep learning techniques. First, a multi-scale superpixel reconstruction method is developed to generate a difference image (DI), which can suppress the speckle noise effectively and enhance edges by exploiting local, spatially homogeneous information. Second, a two-stage centre-constrained fuzzy c -means clustering algorithm is proposed to divide the pixels of the DI into changed, unchanged and intermediate classes with a parallel clustering strategy. Image patches belonging to the first two classes are then constructed as pseudo-label training samples, and image patches of the intermediate class are treated as testing samples. Finally, a convolutional wavelet neural network (CWNN) is designed and trained to classify testing samples into changed or unchanged classes, coupled with a deep convolutional generative adversarial network (DCGAN) to increase the number of changed class within the pseudo-label training samples. Numerical experiments on four real SAR datasets demonstrate the validity and robustness of the proposed approach, achieving up to 99.61% accuracy for small area change detection. [ABSTRACT FROM AUTHOR]