Deepti: Deep-Learning-Based Tropical Cyclone Intensity Estimation System

Maskey, Manil; Ramachandran, Rahul; Ramasubramanian, Muthukumaran; Gurung, Iksha; Freitag, Brian; Kaulfus, Aaron; Bollinger, Drew; Cecil, Daniel J.; Miller, Jeffrey J.

doi:10.1109/jstars.2020.3011907

Cited by 47 publications

(15 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A deep learning model was trained using the curated TC data set with a test root‐mean‐squared error (RMSE) of 13.62 kts (Maskey et al., 2020). This model has a simple convolutional neural network (CNN) architecture using ReLU (Agarap, 2018) as the activation for the final layer to regress the wind speed of the TC for a given image.…”

Section: Benchmarkmentioning

confidence: 99%

See 1 more Smart Citation

Tropical Cyclone Wind Speed Estimation: A Large Scale Training Data Set and Community Benchmarking

Gurung

Ramasubramanian

Freitag

et al. 2023

Earth and Space Science

Self Cite

View full text Add to dashboard Cite

BackgroundTropical cyclones (TCs) cause damage to life and infrastructure, exceeding $10 billion (Blake et al., 2011) in losses in extreme cases. There are numerous factors, including rainfall, wind speed of the TC, and storm surge (NOAA, Hurricanes, 2021), that contribute to the amount of damage. However, due to the spatial scale of wind damage and sparse, low frequency observations over water, estimations of the intensity (wind speed) of TCs is difficult. Hence, methods like the Dvorak technique (Dvorak, 1984), Advanced Dvorak technique (Olander & Velden, 2007), and Deep Learning to Estimate Tropical Cyclone Intensity from Satellite Passive Microwave Imagery (Wimmers et al., 2019) have been developed that use more regularly available satellite observations to estimate the wind speed of TCs (Clarizia et al., 2014;Clarizia & Ruf, 2016).The Dvorak technique (Dvorak, 1984) was initially developed in 1969 and involves human inspection of satellite imagery to observe the specific cloud structure of the TC and classify them into appropriate wind speed categories. This intensity estimation method introduces uncertainty in the estimations due to its dependency on the human interpretation which is inherently subjective. This provides a unique opportunity to utilize the power of ML for TC wind speed estimation. For any supervised ML model to perform well, a well curated, sufficiently large labeled data set is necessary (Virts et al., 2020). Moreover, well curated data are highly sought after within the general ML community as it alleviates the requirement of domain expertise for training ML models. For these purposes, we present a sufficiently large, curated TC wind speed estimation data set based on Geostationary Operational Environmental Satellite (GOES) satellite imagery. The data are presented in a way that can be leveraged to model time-series-based predictions as well as single frame-based regression predictions. GOES satellite imagery, with data available every 10 min (Advanced Baseline Imager, n.d.), has higher temporal resolution than advisories issued by the National Hurricane Center (NHC) (NHC Advisories, 2021), which are released every 6 hr. A model based on these observations can potentially reduce the time between wind-based intensity estimations from 6 hr to 10 min. Furthermore, use of ML model will aid the process of categorization, making the process more efficient while also reducing human induced errors or biases. The estimations from these models can also be analyzed to understand the salient features of a tropical cyclone contributing to their wind speed categorization.

show abstract

Section: Benchmarkmentioning

confidence: 99%

“… Root‐mean‐squared error (RMSE) of top three submissions alongside RMSE of benchmark model using time step (Drivendata Benchmark, 2020) and benchmark model using single image (Maskey et al., 2020). …”

Section: Competitionmentioning

confidence: 99%

Tropical Cyclone Wind Speed Estimation: A Large Scale Training Data Set and Community Benchmarking

Gurung

Ramasubramanian

Freitag

et al. 2023

Earth and Space Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…The AI/ML revolution, driven by a wealth of Open data and rapid technological development in computational cyberinfrastructure, has led to more processing power and greater Networking between cyberinfrastructure as well as data generators and data users which allows unprecedented resource and data sharing. There are many success stories demonstrating how AI/ML has been used to address challenging issues in ESS, for example, extreme weather prediction (Maskey, Ramachandran, et al., 2020; Pradhan et al., 2018; Wimmers et al., 2019), land use/land cover change monitoring (Hansen et al., 2013), Earth system modeling (Reichstein et al., 2019), endangered species identification (Allen et al., 2021), spatial downscaling of climate models and satellite observations (López López et al., 2018; Vandal et al., 2019), space weather forecasting (Wintoft et al., 2017), and lunar and planetary landform classification (Palafox et al., 2017; Silburt et al., 2019). Various funding agencies worldwide have recently released their strategic plans and guidelines to expand the investment in AI/ML research which will further its adoption within informatics for at least the next decade to accelerate scientific discovery and address pressing societal issues such as combatting climate change, facilitating the energy transition, and ensuring food security.…”

Section: Machine Learning For Multiscale Modelingmentioning

confidence: 99%

Earth and Space Science Informatics Perspectives on Integrated, Coordinated, Open, Networked (ICON) Science

Hills

Damerow

Ahmmed

et al. 2022

Earth and Space Science

View full text Add to dashboard Cite

This article is composed of three independent commentaries about the state of Integrated, Coordinated, Open, Networked (ICON) principles (Goldman, et al., 2021b, https://doi. org/10.1029/2021EO153180) in Earth and Space Science Informatics (ESSI) and includes discussion on the opportunities and challenges of adopting them. Each commentary focuses on a different topic: (Section 2) Global collaboration, cyberinfrastructure, and data sharing; (Section 3) Machine learning for multiscale modeling; (Section 4) Aerial and satellite remote sensing for advancing Earth system model development by integrating field and ancillary data. ESSI addresses data management practices, computation and analysis, and hardware and software infrastructure. Our role in ICON science therefore involves collaborative work to assess, design, implement, and promote practices and tools that enable effective data management, discovery, integration, and reuse for interdisciplinary work in Earth and space science disciplines. Networks of diverse people with expertise across Earth, space, and data science disciplines are essential for efficient and ethical exchanges of findable, accessible, interoperable, and reusable (FAIR) research products and practices. Our challenge is then to coordinate the development of standards, curation practices, and tools that enable integrating and reusing multiple data types, software, multi-scale models, and machine learning approaches across disciplines in a way that is as open and/or FAIR as ethically possible. This is a major endeavor that could greatly increase the pace and potential of interdisciplinary scientific discovery. Plain Language SummaryWe present commentaries on the state of "Integrated, Coordinated, Open, Networked (ICON) principles" in Earth and Space Science Informatics. ICON principles are meant to improve the research experience for all. Ultimately, data standardized according to community conventions and formats lead to more effective and efficient collaboration, data discovery, integration, and analyses. Data standards, tools, and machine learning developed using ICON principles enhance our understanding of Earth processes. Using ICON principles improves model results and efficacy, fosters interdisciplinary research, and provides a framework by which non-experts can confidently contribute volunteered data and findings. Standardized data also provides reliable common resources to help train and benchmark machine learning algorithms. When networked communities work together to standardize and share data openly, the resulting web of research products is more readily findable, accessible, interoperable, and reusable. Ongoing support is crucial to develop and sustain the people, systems, and tools necessary to embrace ICON principles in Earth and Space Science Informatics now and in the future.

show abstract

“…In recent works (Giffard-Roisin et al 2020,? ;Maskey et al 2020;Pradhan et al 2018) TC's track and intensity prediction problem is targeted using reanalysis and satellite data.…”

Section: Related Workmentioning

confidence: 99%

Prediction of Landfall Intensity, Location, and Time of a Tropical Cyclone

Kumar

Biswas

Pandey

2021

AAAI

View full text Add to dashboard Cite

The prediction of the intensity, location and time of the landfall of a tropical cyclone well advance in time and with high accuracy can reduce human and material loss immensely. In this article, we develop a Long Short-Term memory based Recurrent Neural network model to predict intensity (in terms of maximum sustained surface wind speed), location (latitude and longitude), and time (in hours after the observation period) of the landfall of a tropical cyclone which originates in the North Indian ocean. The model takes as input the best track data of cyclone consisting of its location, pressure, sea surface temperature, and intensity for certain hours (from 12 to 36 hours) anytime during the course of the cyclone as a time series and then provide predictions with high accuracy. For example, using 24 hours data of a cyclone anytime during its course, the model provides state-of-the-art results by predicting landfall intensity, time, latitude, and longitude with a mean absolute error of 4.24 knots, 4.5 hours, 0.24 degree, and 0.37 degree respectively, which resulted in a distance error of 51.7 kilometers from the landfall location. We further check the efficacy of the model on three recent devastating cyclones Bulbul, Fani, and Gaja, and achieved better results than the test dataset.

show abstract

Deepti: Deep-Learning-Based Tropical Cyclone Intensity Estimation System

Cited by 47 publications

References 28 publications

Tropical Cyclone Wind Speed Estimation: A Large Scale Training Data Set and Community Benchmarking

Tropical Cyclone Wind Speed Estimation: A Large Scale Training Data Set and Community Benchmarking

Earth and Space Science Informatics Perspectives on Integrated, Coordinated, Open, Networked (ICON) Science

Prediction of Landfall Intensity, Location, and Time of a Tropical Cyclone

Contact Info

Product

Resources

About