An official website of the United States government
Revolutionary advances in artificial intelligence (AI) in the past decade have brought transformative innovation across science and engineering disciplines. In the field of Arctic science, we have witnessed an increasing trend in the adoption of AI, especially deep learning, to support the analysis of Arctic big data and facilitate new discoveries. In this paper, we provide a comprehensive review of the applications of deep learning in sea ice remote sensing domains, focusing on problems such as sea ice lead detection, thickness estimation, sea ice concentration and extent forecasting, motion detection, and sea ice type classification. In addition to discussing these applications, we also summarize technological advances that provide customized deep learning solutions, including new loss functions and learning strategies to better understand sea ice dynamics. To promote the growth of this exciting interdisciplinary field, we further explore several research areas where the Arctic sea ice community can benefit from cutting-edge AI technology. These areas include improving multimodal deep learning capabilities, enhancing model accuracy in measuring prediction uncertainty, better leveraging AI foundation models, and deepening integration with physics-based models. We hope that this paper can serve as a cornerstone in the progress of Arctic sea ice research using AI and inspire further advances in this field.
more »
« less
A Review of Practical AI for Remote Sensing in Earth Sciences
Integrating Artificial Intelligence (AI) techniques with remote sensing holds great potential for revolutionizing data analysis and applications in many domains of Earth sciences. This review paper synthesizes the existing literature on AI applications in remote sensing, consolidating and analyzing AI methodologies, outcomes, and limitations. The primary objectives are to identify research gaps, assess the effectiveness of AI approaches in practice, and highlight emerging trends and challenges. We explore diverse applications of AI in remote sensing, including image classification, land cover mapping, object detection, change detection, hyperspectral and radar data analysis, and data fusion. We present an overview of the remote sensing technologies, methods employed, and relevant use cases. We further explore challenges associated with practical AI in remote sensing, such as data quality and availability, model uncertainty and interpretability, and integration with domain expertise as well as potential solutions, advancements, and future directions. We provide a comprehensive overview for researchers, practitioners, and decision makers, informing future research and applications at the exciting intersection of AI and remote sensing.
more »
« less
- PAR ID:
- 10457158
- Publisher / Repository:
- MDPI
- Date Published:
- Journal Name:
- Remote Sensing
- Volume:
- 15
- Issue:
- 16
- ISSN:
- 2072-4292
- Page Range / eLocation ID:
- 4112
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Radio Frequency (RF) sensing has emerged as a pivotal technology for non-intrusive human perception in various applications. However, the challenge of collecting extensive labeled RF data hampers the scalability and effectiveness of machine learning models in this domain. Our prior work introduced innovative generative AI frameworks - RF-Artificial Intelligence Generated Content using conditional generative adversarial networks and RF-Activity Class Conditional Latent Diffusion Model employing latent diffusion models - to synthesize high-quality RF sensing data across multiple platforms. Building upon this foundation, we explore future directions that leverage generative AI for enhanced 3D human pose estimation and beyond. Specifically, we discuss our recent advances in pose completion using latent diffusion transformers and propose additional research avenues: cross-modal generative models for RF sensing, real-time adaptive generative AI incorporating evolutionary learning for dynamic environments, and addressing security and privacy concerns in intelligent cyber-physical systems. These directions aim to further exploit the capabilities of generative AI to overcome challenges in RF sensing, paving the way for more robust, scalable, and secure applications.more » « less
-
Abstract In this review, we explore the growing role of artificial intelligence (AI) in advancing the biomedical applications of human pluripotent stem cell (hPSC)‐derived organoids. Stem cell‐derived organoids, these miniature organ replicas, have become essential tools for disease modeling, drug discovery, and regenerative medicine. However, analyzing the vast and intricate datasets generated from these organoids can be inefficient and error‐prone. AI techniques offer a promising solution to efficiently extract insights and make predictions from diverse data types generated from microscopy images, transcriptomics, metabolomics, and proteomics. This review offers a brief overview of organoid characterization and fundamental concepts in AI while focusing on a comprehensive exploration of AI applications in organoid‐based disease modeling and drug evaluation. It provides insights into the future possibilities of AI in enhancing the quality control of organoid fabrication, label‐free organoid recognition, and three‐dimensional image reconstruction of complex organoid structures. This review presents the challenges and potential solutions in AI‐organoid integration, focusing on the establishment of reliable AI model decision‐making processes and the standardization of organoid research.more » « less
-
Remote sensing datasets usually have a wide range of spatial and spectral resolutions. They provide unique advantages in surveillance systems, and many government organizations use remote sensing multispectral imagery to monitor security-critical infrastructures or targets. Artificial Intelligence (AI) has advanced rapidly in recent years and has been widely applied to remote image analysis, achieving state-of-the-art (SOTA) performance. However, AI models are vulnerable and can be easily deceived or poisoned. A malicious user may poison an AI model by creating a stealthy backdoor. A backdoored AI model performs well on clean data but behaves abnormally when a planted trigger appears in the data. Backdoor attacks have been extensively studied in machine learning-based computer vision applications with natural images. However, much less research has been conducted on remote sensing imagery, which typically consists of many more bands in addition to the red, green, and blue bands found in natural images. In this paper, we first extensively studied a popular backdoor attack, BadNets, applied to a remote sensing dataset, where the trigger was planted in all of the bands in the data. Our results showed that SOTA defense mechanisms, including Neural Cleanse, TABOR, Activation Clustering, Fine-Pruning, GangSweep, Strip, DeepInspect, and Pixel Backdoor, had difficulties detecting and mitigating the backdoor attack. We then proposed an explainable AI-guided backdoor attack specifically for remote sensing imagery by placing triggers in the image sub-bands. Our proposed attack model even poses stronger challenges to these SOTA defense mechanisms, and no method was able to defend it. These results send an alarming message about the catastrophic effects the backdoor attacks may have on satellite imagery.more » « less
-
Unoccupied aerial systems (UAS) are an established technique for collecting data on cold region phenomenon at high spatial and temporal resolutions. While many studies have focused on remote sensing applications for monitoring long term changes in cold regions, the role of UAS for detection, monitoring, and response to rapid changes and direct exposures resulting from abrupt hazards in cold regions is in its early days. This review discusses recent applications of UAS remote sensing platforms and sensors, with a focus on observation techniques rather than post-processing approaches, for abrupt, cold region hazards including permafrost collapse and event-based thaw, flooding, snow avalanches, winter storms, erosion, and ice jams. The pilot efforts highlighted in this review demonstrate the potential capacity for UAS remote sensing to complement existing data acquisition techniques for cold region hazards. In many cases, UASs were used alongside other remote sensing techniques (e.g., satellite, airborne, terrestrial) andin situsampling to supplement existing data or to collect additional types of data not included in existing datasets (e.g., thermal, meteorological). While the majority of UAS applications involved creation of digital elevation models or digital surface models using Structure-from-Motion (SfM) photogrammetry, this review describes other applications of UAS observations that help to assess risks, identify impacts, and enhance decision making. As the frequency and intensity of abrupt cold region hazards changes, it will become increasingly important to document and understand these changes to support scientific advances and hazard management. The decreasing cost and increasing accessibility of UAS technologies will create more opportunities to leverage these techniques to address current research gaps. Overcoming challenges related to implementation of new technologies, modifying operational restrictions, bridging gaps between data types and resolutions, and creating data tailored to risk communication and damage assessments will increase the potential for UAS applications to improve the understanding of risks and to reduce those risks associated with abrupt cold region hazards. In the future, cold region applications can benefit from the advances made by these early adopters who have identified exciting new avenues for advancing hazard research via innovative use of both emerging and existing sensors.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/rs15164112
