Better localized predictions with Out-of-Scope information and Explainable AI: One-Shot SAR backscatter nowcast framework with data from neighboring region

Li, Zhouyayan; Demir, Ibrahim

doi:10.1016/j.isprsjprs.2023.11.021

Cited by 5 publications

(4 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the aggregated information from neighboring areas will be fed into several CNN layers to resume the original image dimension so that the resulting layers with the same dimensions as the localized images can be added or stacked with the localized image patches. As the objective of this work is to introduce the dataset that supports the above-mentioned complex experiments, rather than introducing the algorithms themselves, we highly recommend readers check the previous work by Li & Demir (2024) where we introduced how information from the target and its neighbors are blended and how the SS and SA are implemented in detail.…”

Section: Benchmark Tasks and Evaluation Metrics 31 Overview Of Benchm...mentioning

confidence: 99%

“…In this work, we accepted the configurations for information blending introduced in the work done by Li & Demir (2024). Specifically, we will consider neighbors within 5 hops (5 moves in total, following D8 flow directions) of the target image patch.…”

Section: Benchmark Tasks and Evaluation Metrics 31 Overview Of Benchm...mentioning

confidence: 99%

“…In their study, the authors synthesized Sentinel-1 SAR images at the pixel level using geomorphic datasets, SAR images obtained one revisit cycle (12 days) prior to the target time, and precipitation and soil moisture measurements obtained within 7 days prior to the target time. Building on top of that work, Li & Demir (2024) introduced two deep-learningbased frameworks, SA, and SS, to blend localized inputs with information from neighboring areas of target regions for improved performance.…”

Section: Introductionmentioning

confidence: 99%

“…All possible distance combinations within the 5-hop scope of any target patches. The table was adapted from Table1of the work done byLi & Demir (2024).…”

mentioning

confidence: 99%

See 3 more Smart Citations

EarthObsNet: A Comprehensive Benchmark Dataset for Data-Driven Earth Observation Image Synthesis

Li,

Sermet,

Demir

2024

Preprint

View full text Add to dashboard Cite

Remote Sensing imagery serves as an important data source for Earth surface monitoring and surface processes studies. It is highly likely that RS imagery will become more and more indispensable in the future due to its high scalability and compatibility with data-driven models and ever-evolving software and hardware that become increasingly good at processing large datasets. Although its promising future, the usage of Earth surface observation imagery, such as Landsat, Sentinel-2, and Sentinel-1 images, has been largely limited to retrospective studies, where those images serve mainly as documentations of past events. Recently, there are attempts to expand the current usage of RS Earth surface observation images to forward-looking applications to support decision-making and fast response against future natural hazards. Unlike many well-defined and well-studied topics such as change detection and semantic segmentation for which many benchmark datasets are openly available, so far, there are limited public datasets for Earth surface observation image synthesis tasks for fast prototyping and comparison. To close this gap, we introduced a comprehensive dataset containing previous Earth surface observations, precipitation, soil moisture, land cover, Height Above Nearest Drainage (HAND), DEM, and slope collected during the catastrophic 2019 Central US Flooding events that lasted more than two seasons in Mississippi and Missouri River tributaries. We also incorporated reference labels to allow further investigation of the usefulness of the synthesized images in downstream applications, such as flood inundation mapping. We hope to provide an essential dataset for Earth observation image synthesis studies, with the goal of attracting more attention and inspiring more efforts to broaden the usage of Earth surface observation images into forward-looking applications.

show abstract

Section: Benchmark Tasks and Evaluation Metrics 31 Overview Of Benchm...mentioning

confidence: 99%

Section: Benchmark Tasks and Evaluation Metrics 31 Overview Of Benchm...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…All possible distance combinations within the 5-hop scope of any target patches. The table was adapted from Table1of the work done byLi & Demir (2024).…”

mentioning

confidence: 99%

See 2 more Smart Citations

EarthObsNet: A Comprehensive Benchmark Dataset for Data-Driven Earth Observation Image Synthesis

Li,

Sermet,

Demir

2024

Preprint

View full text Add to dashboard Cite

show abstract

Integrating vision‐based AI and large language models for real‐time water pollution surveillance

Samuel,

Sermet,

Cwiertny

et al. 2024

Water Environment Research

View full text Add to dashboard Cite

Water pollution has become a major concern in recent years, affecting over 2 billion people worldwide, according to UNESCO. This pollution can occur by either naturally, such as algal blooms, or man‐made when toxic substances are released into water bodies like lakes, rivers, springs, and oceans. To address this issue and monitor surface‐level water pollution in local water bodies, an informative real‐time vision‐based surveillance system has been developed in conjunction with large language models (LLMs). This system has an integrated camera connected to a Raspberry Pi for processing input frames and is further linked to LLMs for generating contextual information regarding the type, causes, and impact of pollutants on both human health and the environment. This multi‐model setup enables local authorities to monitor water pollution and take necessary steps to mitigate it. To train the vision model, seven major types of pollutants found in water bodies like algal bloom, synthetic foams, dead fishes, oil spills, wooden logs, industrial waste run‐offs, and trashes were used for achieving accurate detection. ChatGPT API has been integrated with the model to generate contextual information about pollution detected. Thus, the multi‐model system can conduct surveillance over water bodies and autonomously alert local authorities to take immediate action, eliminating the need for human intervention.Practitioner Points Combines cameras and LLMs with Raspberry Pi for processing and generating pollutant information. Uses YOLOv5 to detect algal blooms, synthetic foams, dead fish, oil spills, and industrial waste. Supports various modules and environments, including drones and mobile apps for broad monitoring. Educates on environmental healthand alerts authorities about water pollution.

show abstract

MultiRS flood mapper: a google earth engine application for water extent mapping with multimodal remote sensing and quantile-based postprocessing

Li,

Demir

2024

Environmental Modelling & Software

View full text Add to dashboard Cite

Better localized predictions with Out-of-Scope information and Explainable AI: One-Shot SAR backscatter nowcast framework with data from neighboring region

Cited by 5 publications

References 59 publications

EarthObsNet: A Comprehensive Benchmark Dataset for Data-Driven Earth Observation Image Synthesis

EarthObsNet: A Comprehensive Benchmark Dataset for Data-Driven Earth Observation Image Synthesis

Integrating vision‐based AI and large language models for real‐time water pollution surveillance

MultiRS flood mapper: a google earth engine application for water extent mapping with multimodal remote sensing and quantile-based postprocessing

Contact Info

Product

Resources

About