pith. sign in

arxiv: 2307.10803 · v2 · submitted 2023-07-20 · 💻 cs.LG · cs.AI· physics.ao-ph

Spatial-Temporal Data Mining for Ocean Science: Data, Methodologies, and Opportunities

Hanchen Yang , Wengen Li , Shuyu Wang , Hui Li , Jihong Guan , Shuigeng Zhou , Jiannong Cao This is my paper

Pith reviewed 2026-05-24 07:33 UTC · model grok-4.3

classification 💻 cs.LG cs.AIphysics.ao-ph
keywords spatial-temporal data miningocean sciencesurveypredictionevent detectionpattern mininganomaly detectiondata quality
0
0 comments X

The pith

This survey fills the gap by classifying spatial-temporal data mining studies for ocean science into prediction, event detection, pattern mining, and anomaly detection.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes that a missing comprehensive review of spatial-temporal data mining on ocean data can be supplied by first examining widely used datasets and their traits such as diverse regionality and high sparsity, then covering quality enhancement steps, and finally grouping existing work under four task headings. A sympathetic reader would care because these data traits complicate model design and training compared with typical spatial-temporal sources like traffic records, so the structure helps computer scientists spot open problems and ocean scientists adopt suitable techniques for issues like climate forecasting. The survey ends by pointing to promising research directions that follow from the reviewed methods.

Core claim

The paper's central claim is that, to the best of our knowledge, no prior comprehensive survey exists, and the present work supplies one by reviewing widely-used spatial-temporal ocean datasets and their unique characteristics, exploring typical data quality enhancement techniques, classifying existing studies into the four task types of prediction, event detection, pattern mining, and anomaly detection with elaboration on the techniques for each, and finally discussing promising research opportunities; this organization assists scientists in both computer science and ocean science with fundamental concepts, key techniques, and open challenges.

What carries the argument

The four-task classification (prediction, event detection, pattern mining, anomaly detection) that organizes existing spatial-temporal data mining studies applied to ocean data and their associated techniques.

If this is right

  • Computer scientists gain clearer identification of research issues specific to ocean data mining.
  • Ocean scientists gain easier access to advanced spatial-temporal data mining techniques for problems such as climate forecasting and disaster warning.
  • The unique data characteristics of regionality and sparsity receive explicit attention when designing new models.
  • Open challenges highlighted at the end can directly shape subsequent studies in the area.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Similar classification schemes could be tested on spatial-temporal data from other domains that share sparsity or regionality traits.
  • The reviewed datasets could function as shared benchmarks once the survey makes them more visible across fields.
  • If new ocean data sources appear with traits not captured here, the four-category structure may require an added task type.

Load-bearing premise

That the four chosen task categories together with the reviewed datasets are representative of the full range of existing spatial-temporal data mining work on ocean data.

What would settle it

A substantial collection of spatial-temporal data mining papers on ocean science whose methods or datasets fall outside the four task categories and the reviewed sources.

Figures

Figures reproduced from arXiv: 2307.10803 by Hanchen Yang, Hui Li, Jiannong Cao, Jihong Guan, Shuigeng Zhou, Shuyu Wang, Wengen Li.

Figure 1
Figure 1. Figure 1: The illustration of STDM for ocean science, which [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 3
Figure 3. Figure 3: The content and organization of this survey. [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Satellite data collection and inversion. (a) Satellite data collection with different bands [ [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: The global distribution of Argo sensors in 2023 [ [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
Figure 7
Figure 7. Figure 7: The visualization of ship trajectories in the Automatic Identification System (AIS) [ [PITH_FULL_IMAGE:figures/full_fig_p009_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: The visualizations of ocean environmental elements: (a) The global SST at different depths [ [PITH_FULL_IMAGE:figures/full_fig_p012_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: The visualization of typhoon Hato at 04:00 [PITH_FULL_IMAGE:figures/full_fig_p012_9.png] view at source ↗
Figure 11
Figure 11. Figure 11: Distributions and missing rates of global SST and Chl-a data. (a) / (b) The spatial distribution of SST / [PITH_FULL_IMAGE:figures/full_fig_p014_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: The general framework of ST data completion, where the input is incomplete ST data, the output is [PITH_FULL_IMAGE:figures/full_fig_p014_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: A mapping from the data sources to the data instances and the four types of ocean STDM tasks. [PITH_FULL_IMAGE:figures/full_fig_p018_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: A taxonomy of methodologies of different ocean STDM tasks. [PITH_FULL_IMAGE:figures/full_fig_p019_14.png] view at source ↗
Figure 15
Figure 15. Figure 15: The distribution of publications of various ocean STDM tasks (data from the Web of Science. [PITH_FULL_IMAGE:figures/full_fig_p019_15.png] view at source ↗
Figure 16
Figure 16. Figure 16: The framework of the CLCRN model, which is implemented based on the Sequence to Sequence [PITH_FULL_IMAGE:figures/full_fig_p021_16.png] view at source ↗
Figure 17
Figure 17. Figure 17: The framework of data-attention-YOLO for eddy identification. Here, (a) the two input datasets, (b) [PITH_FULL_IMAGE:figures/full_fig_p026_17.png] view at source ↗
Figure 18
Figure 18. Figure 18: Spatial distributions (a,b,c) and time series (d,e,f ) of the SST anomalies of the first three modes by [PITH_FULL_IMAGE:figures/full_fig_p028_18.png] view at source ↗
Figure 19
Figure 19. Figure 19: The visualization of AIS trajectories and the corresponding detection results of three trajectory [PITH_FULL_IMAGE:figures/full_fig_p030_19.png] view at source ↗
read the original abstract

With the rapid amassing of spatial-temporal (ST) ocean data, many spatial-temporal data mining (STDM) studies have been conducted to address various oceanic issues, including climate forecasting and disaster warning. Compared with typical ST data (e.g., traffic data), ST ocean data is more complicated but with unique characteristics, e.g., diverse regionality and high sparsity. These characteristics make it difficult to design and train STDM models on ST ocean data. To the best of our knowledge, a comprehensive survey of existing studies remains missing in the literature, which hinders not only computer scientists from identifying the research issues in ocean data mining but also ocean scientists to apply advanced STDM techniques. In this paper, we provide a comprehensive survey of existing STDM studies for ocean science. Concretely, we first review the widely-used ST ocean datasets and highlight their unique characteristics. Then, typical ST ocean data quality enhancement techniques are explored. Next, we classify existing STDM studies in ocean science into four types of tasks, i.e., prediction, event detection, pattern mining, and anomaly detection, and elaborate on the techniques for these tasks. Finally, promising research opportunities are discussed. This survey can help scientists from both computer science and ocean science better understand the fundamental concepts, key techniques, and open challenges of STDM for ocean science.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper claims to deliver the first comprehensive survey of spatial-temporal data mining (STDM) for ocean science. It reviews widely-used ST ocean datasets and their unique characteristics (e.g., regionality and sparsity), covers data quality enhancement techniques, classifies existing studies into four task categories (prediction, event detection, pattern mining, anomaly detection), elaborates on techniques within each category, and discusses promising research opportunities. The central assertion is that no such survey previously existed and that the four-category taxonomy organizes the literature.

Significance. A well-executed survey with an exhaustive, reproducible paper selection process and a defensible taxonomy would fill a documented gap, help computer scientists identify ocean-specific modeling challenges, and assist ocean scientists in locating relevant STDM methods. The explicit discussion of dataset characteristics and the four-task structure are useful organizing devices if they are shown to be representative.

major comments (1)
  1. [Abstract, §1] Abstract and §1: the claim that 'to the best of our knowledge, a comprehensive survey of existing studies remains missing' and that the paper supplies one is load-bearing for the entire contribution, yet no literature-search protocol (databases, keywords, date range, inclusion/exclusion criteria, or total papers screened) is provided. Without this, it is impossible to assess whether the four-task taxonomy is exhaustive or whether important boundary cases have been omitted or forced into one bin.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback. The concern about the missing literature-search protocol is valid and directly affects the strength of our contribution claim. We address it below.

read point-by-point responses

  1. Referee: [Abstract, §1] Abstract and §1: the claim that 'to the best of our knowledge, a comprehensive survey of existing studies remains missing' and that the paper supplies one is load-bearing for the entire contribution, yet no literature-search protocol (databases, keywords, date range, inclusion/exclusion criteria, or total papers screened) is provided. Without this, it is impossible to assess whether the four-task taxonomy is exhaustive or whether important boundary cases have been omitted or forced into one bin.

    Authors: We agree that the original manuscript does not supply an explicit search protocol, which limits the ability to verify exhaustiveness. In the revised version we will add a dedicated paragraph (or short subsection) in §1 that states the databases consulted, the keyword combinations employed, the primary date range, and the inclusion criteria used to assign papers to the four task categories. This addition will also note how boundary cases were handled. The four-category taxonomy was derived from the dominant problem formulations appearing in the collected STDM-ocean literature rather than from a pre-defined exhaustive list; the protocol description will make the selection process transparent so readers can judge coverage themselves. revision: yes

Circularity Check

0 steps flagged

No circularity: survey taxonomy is organizational, not derivational

full rationale

This is a literature review paper with no equations, models, parameter fitting, or predictive derivations. The four-task classification (prediction, event detection, pattern mining, anomaly detection) is presented as an organizing framework for existing studies rather than a result derived from data or self-referential definitions. No load-bearing self-citations, uniqueness theorems, or ansatzes appear. The claim of being the first comprehensive survey rests on the authors' selection of papers, but that is an empirical completeness issue, not a circular reduction of any claimed derivation to its own inputs. The paper is self-contained as a survey.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a literature survey the paper introduces no free parameters, mathematical axioms, or invented entities; it rests entirely on the body of existing published studies.

pith-pipeline@v0.9.0 · 5794 in / 1084 out tokens · 34630 ms · 2026-05-24T07:33:45.509354+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. OKG-LLM: Aligning Ocean Knowledge Graph with Observation Data via LLMs for Global Sea Surface Temperature Prediction

    cs.LG 2025-07 unverdicted novelty 7.0

    OKG-LLM constructs an Ocean Knowledge Graph, learns its embeddings, fuses them with SST observations, and applies an LLM to outperform prior methods on global sea surface temperature prediction.

  2. An Adaptive Spatiotemporal Clustering Framework for 3D Ocean Subsurface Temperature Reconstruction

    physics.ao-ph 2026-04 unverdicted novelty 5.0

    An adaptive spatiotemporal clustering framework boosts deep learning reconstruction of global ocean subsurface temperature fields from surface data, delivering 12.4% to 27.2% RMSE improvements when paired with models ...

Reference graph

Works this paper leans on

299 extracted references · 299 canonical work pages · cited by 2 Pith papers · 3 internal anchors

  1. [1]

    Argo Floats to Improve Our Knowledge of the Ocean

    2018. Argo Floats to Improve Our Knowledge of the Ocean. https://www.euro-argo.eu/Outreach/Educational- material/Discover-Argo-floats/How-do-the-Argo-floats-fulfill-their-mission-in-the-Ocean, Last accessed on 2018- 10-25

    work page 2018

  2. [2]

    ArcGIS Pro

    2020. ArcGIS Pro. https://www.esriuk.com/en-gb/arcgis/, Last accessed on 2020-8-11. J. ACM, Vol. 37, No. 4, Article 111. Publication date: July 2023. Spatial-Temporal Data Mining for Ocean Science: Data, Methodologies and Opportunities 111:33

    work page 2020

  3. [3]

    2021. AVHRR. https://www.eumetsat.int/avhrr, Last accessed on 2021-10-03

    work page 2021

  4. [4]

    2021. MODIS. https://modis.gsfc.nasa.gov/gallery/, Last accessed on 2021-10-03

    work page 2021

  5. [5]

    The visualization of trajectories of automatic identification system

    2023. The visualization of trajectories of automatic identification system. https://www.marinetraffic.com/research/ dataset/marinetraffic-automatic-identification-system-ais/, Last accessed on 2023-1-25

    work page 2023

  6. [6]

    The workflow of Argo sensors

    2023. The workflow of Argo sensors. https://globalocean.noaa.gov/research/argo-program/, Last accessed on 2023-1-2

    work page 2023

  7. [7]

    Tri Dev Acharya, Kyung Wan Yoo, and Dong Ha Lee. 2017. GIS-based Spatio-temporal Analysis of Marine Accidents Database in the Coastal Zone of Korea. Journal of Coastal Research 79, sp1 (2017), 114 – 118

    work page 2017

  8. [8]

    Silvestre Aguilar-Martinez and William W. Hsieh. 2009. Forecasts of Tropical Pacific Sea Surface Temperatures by Neural Networks and Support Vector Regression. International Journal of Oceanography (2009), 1–13

    work page 2009

  9. [9]

    Muhammad Aurangzeb Ahmad and Şener Özönder. 2020. Physics inspired models in artificial intelligence. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . 3535–3536

    work page 2020

  10. [10]

    Sheila Alemany, Jonathan Beltran, Adrian Perez, and Sam Ganzfried. 2019. Predicting hurricane trajectories using a recurrent neural network. In Proceedings of the AAAI Conference on Artificial Intelligence , Vol. 33. 468–475

    work page 2019

  11. [11]

    MM Ali, CM Kishtawal, and Sarika Jain. 2007. Predicting cyclone tracks in the north Indian Ocean: An artificial neural network approach. Geophysical research letters 34, 4 (2007)

    work page 2007

  12. [12]

    Alvera-Azcárate, A

    A. Alvera-Azcárate, A. Barth, J.-M. Beckers, and R. H. Weisberg. 2007. Multivariate Reconstruction of Missing Data in Sea Surface Temperature, Chlorophyll, and Wind Satellite Fields. Journal of Geophysical Research 112, C3 (2007)

    work page 2007

  13. [13]

    Aïda Alvera-Azcárate, Alexander Barth, Michel Rixen, and Jean-Marie Beckers. 2005. Reconstruction of incomplete oceanographic data sets using empirical orthogonal functions: application to the Adriatic Sea surface temperature. Ocean Modelling 9, 4 (2005), 325–346

    work page 2005

  14. [14]

    Tao Cheng Berk Anbaroğlu. 2009. Spatio-temporal outlier detection in environmental data. Spatial and Temporal Reasoning for Ambient Intelligence Systems (2009), 1–10

    work page 2009

  15. [15]

    Mathias Anneken, Yvonne Fischer, and Jürgen Beyerer. 2015. Evaluation and comparison of anomaly detection algorithms in annotated datasets from the maritime domain. In 2015 SAI Intelligent Systems Conference (IntelliSys) . IEEE, 169–178

    work page 2015

  16. [16]

    Lotfi Aouf, Danièle Hauser, Celine Tison, and Bertrand Chapron. 2018. On the Assimilation of Multi-Source of Directional Wave Spectra from Sentinel-1A and 1B, and CFOSAT in the Wave Model MFWAM: Toward an Operational Use in CMEMS-MFC. In 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018, Valencia, Spain, July 22-27, 2018 . IEEE,...

    work page 2018

  17. [17]

    Jong-Jin Baik and Jong-Su Paek. 2000. A neural network model for predicting typhoon intensity. Journal of the Meteorological Society of Japan. Ser. II 78, 6 (2000), 857–869

    work page 2000

  18. [18]

    Banks, Christine Gommenginger, Meric Srokosz, and Helen M

    Christopher J. Banks, Christine Gommenginger, Meric Srokosz, and Helen M. Snaith. 2012. Validating SMOS Ocean Surface Salinity in the Atlantic With Argo and Operational Ocean Model Data. IEEE Trans. Geosci. Remote. Sens. 50, 5-1 (2012), 1688–1702

    work page 2012

  19. [19]

    Donald Barrick, Vicente Fernandez, Maria I Ferrer, Chad Whelan, and Øyvind Breivik. 2012. A short-term predictive system for surface currents from a rapidly deployed coastal HF radar network. Ocean Dynamics 62 (2012), 725–740

    work page 2012

  20. [20]

    Alexander Barth, Aida Alvera-Azcárate, Matjaz Licer, and Jean-Marie Beckers. 2020. DINCAE 1.0: A Convolutional Neural Network with Error Estimates to Reconstruct Sea Surface Temperature Satellite Observations. Geoscientific Model Development 13, 3 (2020), 1609–1622

    work page 2020

  21. [21]

    Patrick M Bartier and C Peter Keller. 1996. Multivariate interpolation to incorporate thematic surface data using inverse distance weighting (IDW). Computers & Geosciences 22, 7 (1996), 795–799

    work page 1996

  22. [22]

    Sajib Barua and Reda Alhajj. 2007. Parallel wavelet transform for spatio-temporal outlier detection in large mete- orological data. In Intelligent Data Engineering and Automated Learning-IDEAL 2007: 8th International Conference, Birmingham, UK, December 16-19, 2007. Proceedings 8 . Springer, 684–694

    work page 2007

  23. [23]

    J. M. Beckers and M. Rixen. 2003. EOF Calculations and Data Filling from Incomplete Oceanographic Datasets*. Journal of Atmospheric and Oceanic Technology 20, 12 (2003), 1839–1856

    work page 2003

  24. [24]

    Tata V. S. Udaya Bhaskar and Chiranjivi Jayaram. 2015. Evaluation of Aquarius Sea Surface Salinity With Argo Sea Surface Salinity in the Tropical Indian Ocean. IEEE Geosci. Remote. Sens. Lett. 12, 6 (2015), 1292–1296

    work page 2015

  25. [25]

    Shrutilipi Bhattacharjee, Pabitra Mitra, and Soumya K. Ghosh. 2014. Spatial Interpolation to Predict Missing Attributes in GIS Using Semantic Kriging. IEEE Transactions on Geoscience and Remote Sensing 52, 8 (2014), 4771–4780

    work page 2014

  26. [26]

    Kaifeng Bi, Lingxi Xie, Hengheng Zhang, Xin Chen, Xiaotao Gu, and Qi Tian. 2023. Accurate medium-range global weather forecasting with 3D neural networks. Nature (2023), 1–6

    work page 2023

  27. [27]

    Nguyen An Binh, Pham Viet Hoa, Giang Thi Phuong Thao, Ho Dinh Duan, and Phan Minh Thu. 2022. Evaluation of Chlorophyll-a estimation using Sentinel 3 based on various algorithms in southern coastal Vietnam. Int. J. Appl. Earth Obs. Geoinformation 112 (2022), 102951. J. ACM, Vol. 37, No. 4, Article 111. Publication date: July 2023. 111:34 Hanchen Yang, Weng...

    work page 2022

  28. [28]

    François Boy, Jean-François Crétaux, Malik Boussaroque, and Céline Tison. 2022. Improving Sentinel-3 SAR Mode Processing Over Lake Using Numerical Simulations. IEEE Trans. Geosci. Remote. Sens. 60 (2022), 1–18

    work page 2022

  29. [29]

    Timothy P Boyer, John I Antonov, Olga K Baranova, Hernan E Garcia, Daphne R Johnson, Alexey V Mishonov, Todd D O’Brien, Dan Seidov, Igor Smolyar, Melissa M Zweng, et al. 2013. World ocean database 2013. (2013)

    work page 2013

  30. [30]

    Bruno Brandoli, Alessandra Raffaetà, Marta Simeoni, Pedram Adibi, Fateha Khanam Bappee, Fabio Pranovi, Giulia Rovinelli, Elisabetta Russo, Claudio Silvestri, Amílcar Soares, and Stan Matwin. 2022. From multiple aspect trajectories to predictive analysis: a case study on fishing vessels in the Northern Adriatic sea. GeoInformatica 26, 4 (2022), 551–579

    work page 2022

  31. [31]

    Buongiorno Nardelli, C

    B. Buongiorno Nardelli, C. Tronconi, A. Pisano, and R. Santoleri. 2013. High and Ultra-High resolution processing of satellite Sea Surface Temperature data over Southern European Seas in the framework of MyOcean project. Remote Sensing of Environment 129 (2013), 1–16

    work page 2013

  32. [32]

    Wen-Yu Cai, Zi-Qiang Liu, and Mei-Yan Zhang. 2019. Trajectory Clustering Based Oceanic Anomaly Detection Using Argo Profile Floats. In Communications and Networking - 14th EAI International Conference, ChinaCom 2019, Shanghai, China, November 29 - December 1, 2019, Proceedings, Part I (Lecture Notes of the Institute for Computer Sciences, Social Informati...

    work page 2019

  33. [33]

    Mark A Cane, Stephen E Zebiak, and Sean C Dolan. 1986. Experimental forecasts of EL Nino. Nature 321, 6073 (1986), 827–832

    work page 1986

  34. [34]

    Talley, Kevin Speer, Cathrine Hancock, and Stephen Riser

    Paul Chamberlain, Bruce Cornuelle, Lynne D. Talley, Kevin Speer, Cathrine Hancock, and Stephen Riser. 2023. Acoustic Float Tracking with the Kalman Smoother. Journal of Atmospheric and Oceanic Technology 40, 1 (2023), 15–35

    work page 2023

  35. [35]

    Chelton, Michael G

    Dudley B. Chelton, Michael G. Schlax, and Roger M. Samelson. 2011. Global observations of nonlinear mesoscale eddies. Progress in Oceanography 91, 2 (2011), 167–216

    work page 2011

  36. [36]

    Jianqiang Chen, Xun Gong, Xinyu Guo, Xiaogang Xing, Keyu Lu, Huiwang Gao, and Xiang Gong. 2022. Improved Perceptron of Subsurface Chlorophyll Maxima by a Deep Neural Network: A Case Study with BGC-Argo Float Data in the Northwestern Pacific Ocean. Remote. Sens. 14, 3 (2022), 632

    work page 2022

  37. [37]

    Rui Chen, Xiang Wang, Weimin Zhang, Xiaoyu Zhu, Aiping Li, and Chao Yang. 2019. A hybrid CNN-LSTM model for typhoon formation forecasting. GeoInformatica 23 (2019), 375–396

    work page 2019

  38. [38]

    Barnes, Yuyuan Xie, Gong Lin, and Zhongfeng Qiu

    Shuangling Chen, Chuanmin Hu, Brian B. Barnes, Yuyuan Xie, Gong Lin, and Zhongfeng Qiu. 2019. Improving Ocean Color Data Coverage through Machine Learning. Remote Sensing of Environment 222 (2019), 286–302

    work page 2019

  39. [39]

    Wei Chen and Bo-Cai Gao. 2013. A Multispectral Decomposition Technique for the Recovery of True SeaWiFS Top-of-Atmosphere Radiances. IEEE Geosci. Remote. Sens. Lett. 10, 2 (2013), 288–292

    work page 2013

  40. [40]

    Randerson, Douglas C

    Yang Chen, James T. Randerson, Douglas C. Morton, Ruth S. DeFries, G. James Collatz, Prasad S. Kasibhatla, Louis Giglio, Yufang Jin, and Miriam E. Marlier. 2011. Forecasting Fire Season Severity in South America Using Sea Surface Temperature Anomalies. Science 334, 6057 (2011), 787–791

    work page 2011

  41. [41]

    Zhuomin Chen, Young-Oh Kwon, Ke Chen, Paula Fratantoni, Glen Gawarkiewicz, and Terrence M Joyce. 2020. Long-term SST variability on the Northwest Atlantic continental shelf and slope. Geophysical Research Letters 47, 1 (2020), e2019GL085455

    work page 2020

  42. [42]

    Tao Cheng and Zhilin Li. 2006. A multiscale approach for spatio-temporal outlier detection. Transactions in GIS 10, 2 (2006), 253–263

    work page 2006

  43. [43]

    Xinhua Cheng and John M Wallace. 1993. Cluster analysis of the Northern Hemisphere wintertime 500-hPa height field: Spatial patterns. Journal of atmospheric sciences 50, 16 (1993), 2674–2696

    work page 1993

  44. [44]

    Junhwa Chi and Hyun-choel Kim. 2017. Prediction of arctic sea ice concentration using a fully data driven deep neural network. Remote Sensing 9, 12 (2017), 1305

    work page 2017

  45. [45]

    Hone-Jay Chu, Churn-Jung Liau, Chao-Hung Lin, and Bo-Song Su. 2012. Integration of fuzzy cluster analysis and kernel density estimation for tracking typhoon trajectories in the Taiwan region. Expert Systems with Applications 39, 10 (2012), 9451–9457

    work page 2012

  46. [46]

    Kevin Cowtan and Robert G Way. 2014. Coverage bias in the HadCRUT4 temperature series and its impact on recent temperature trends. Quarterly Journal of the Royal Meteorological Society 140, 683 (2014), 1935–1944

    work page 2014

  47. [47]

    Noel Cressie and Christopher K Wikle. 2015. Statistics for spatio-temporal data . John Wiley & Sons

    work page 2015

  48. [48]

    Noel A Cressie. 1996. Change of support and the modifiable areal unit problem. (1996)

    work page 1996

  49. [49]

    WP Crowley. 1968. A global numerical ocean model: Part I. J. Comput. Phys. 3, 1 (1968), 111–147

    work page 1968

  50. [50]

    Tamraparni Dasu and Ji Meng Loh. 2012. Statistical Distortion: Consequences of Data Cleaning. Proceedings of the VLDB Endowment 5, 11 (2012)

    work page 2012

  51. [51]

    Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  52. [52]

    Henk A Dijkstra. 2005. Nonlinear physical oceanography: a dynamical systems approach to the large scale ocean circulation and El Niño . Vol. 532. Springer. J. ACM, Vol. 37, No. 4, Article 111. Publication date: July 2023. Spatial-Temporal Data Mining for Ocean Science: Data, Methodologies and Opportunities 111:35

    work page 2005

  53. [53]

    Zizhen Dong, Ruowen Yang, Jie Cao, and Lin Wang. 2023. Effect of Anthropogenic Forcing on Increased Winter Precipitation in Southeast Asia from 1979 to 2014. Frontiers in Environmental Science 10 (2023), 2723

    work page 2023

  54. [54]

    Sheldon D Drobot, James A Maslanik, and Charles Fowler. 2006. A long-range forecast of Arctic summer sea-ice minimum extent. Geophysical Research Letters 33, 10 (2006)

    work page 2006

  55. [55]

    Mei Du, Yijun Hou, Po Hu, and Kai Wang. 2020. Effects of typhoon paths on storm surge and coastal inundation in the Pearl River Estuary, China. Remote Sensing 12, 11 (2020), 1851

    work page 2020

  56. [56]

    Mengnan Du, Ninghao Liu, and Xia Hu. 2019. Techniques for interpretable machine learning. Commun. ACM 63, 1 (2019), 68–77

    work page 2019

  57. [57]

    Yanling Du, Wei Song, Qi He, Dongmei Huang, Antonio Liotta, and Chen Su. 2019. Deep learning with multi-scale feature fusion in remote sensing for automatic oceanic eddy detection. Information Fusion 49 (2019), 89–99

    work page 2019

  58. [58]

    Lian Duan, Lida Xu, Ying Liu, and Jun Lee. 2009. Cluster-based outlier detection. Annals of Operations Research 168 (2009), 151–168

    work page 2009

  59. [59]

    Bradley Efron and Robert Tibshirani. 1991. Statistical Data Analysis in the Computer Age. Science 253, 5018 (1991), 390–395

    work page 1991

  60. [60]

    Jeffrey L Elman. 1990. Finding structure in time. Cognitive science 14, 2 (1990), 179–211

    work page 1990

  61. [61]

    Elvidge, Tilottama Ghosh, Feng-Chi Hsu, and Mikhail N

    Christopher D. Elvidge, Tilottama Ghosh, Feng-Chi Hsu, and Mikhail N. Zhizhin. 2022. VIIRS Monitoring and Reporting on Lit Fishing Vessel Detections in Southeast Asia. In IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022, Kuala Lumpur, Malaysia, July 17-22, 2022 . IEEE, 4779–4782

    work page 2022

  62. [62]

    Faghmous and Vipin Kumar

    James H. Faghmous and Vipin Kumar. 2014. Spatio-Temporal Data Mining for Climate Data: Advances, Challenges, and Opportunities. In Data Mining and Knowledge Discovery for Big Data . Vol. 1. Springer Berlin Heidelberg, Berlin, Heidelberg, 83–116

    work page 2014

  63. [63]

    C Fahn, Jer Ling, M Yeh, P Huang, and M Wu. 2019. Abnormal maritime activity detection in satellite image sequences using trajectory features. International Journal of Future Computer and Communication 8, 1 (2019), 29–33

    work page 2019

  64. [64]

    Feng-Lei Fan, Jinjun Xiong, Mengzhou Li, and Ge Wang. 2021. On interpretability of artificial neural networks: A survey. IEEE Transactions on Radiation and Plasma Medical Sciences 5, 6 (2021), 741–760

    work page 2021

  65. [65]

    Rubén Fernández-Beltran, Damian Ibañez, Jian Kang, and Filiberto Pla. 2022. Time-Resolved Sentinel-3 Vegetation Indices Via Inter-Sensor 3-D Convolutional Regression Networks. IEEE Geosci. Remote. Sens. Lett. 19 (2022), 1–5

    work page 2022

  66. [66]

    Martha Dais Ferreira, Jessica NA Campbell, and Stan Matwin. 2022. A novel machine learning approach to analyzing geospatial vessel patterns using AIS data. GIScience & Remote Sensing 59, 1 (2022), 1473–1490

    work page 2022

  67. [67]

    Luciano Floridi and Massimo Chiriatti. 2020. GPT-3: Its nature, scope, limits, and consequences. Minds and Machines 30 (2020), 681–694

    work page 2020

  68. [68]

    Nicola Forti, Leonardo M Millefiori, Paolo Braca, and Peter Willett. 2021. Bayesian filtering for dynamic anomaly detection and tracking. IEEE Trans. Aerospace Electron. Systems 58, 3 (2021), 1528–1544

    work page 2021

  69. [69]

    Sergey Frolov, Jeffrey Paduan, Michael Cook, and James Bellingham. 2012. Improved statistical prediction of surface currents based on historic HF-radar observations. Ocean Dynamics 62 (2012), 1111–1122

    work page 2012

  70. [70]

    M. M. Galotto-Tébar, A. Pomares-Padilla, I. A. Czerwinski, and J. C. Gutiérrez-Estrada. 2022. Is the vessel fishing? Discrimination of fishing activity with low-cost intelligent mobile devices through traditional and heuristic approaches. Expert Syst. Appl. 200 (2022), 117091

    work page 2022

  71. [71]

    Yanqiu Gao, Youmin Tang, Xunshu Song, and Zheqi Shen. 2021. Parameter Estimation Based on a Local Ensemble Transform Kalman Filter Applied to El Niño–Southern Oscillation Ensemble Prediction. Remote Sensing 13, 19 (2021), 3923

    work page 2021

  72. [72]

    Augustine-Moses Gaavwase Gbagir and Alfred Colpaert. 2020. Assessing the Trend of the Trophic State of Lake Ladoga Based on Multi-Year (1997-2019) CMEMS GlobColour-Merged CHL-OC5 Satellite Observations. Sensors 20, 23 (2020), 6881

    work page 2020

  73. [73]

    Richard L. S. F. George, Peter E. Robins, Alan G. Davies, Panagiotis D. Ritsos, and Jonathan C. Roberts. 2014. Interactive Visual Analytics of Hydrodynamic Flux for the Coastal Zone. Environmental Earth Sciences 72, 10 (2014), 3753–3766

    work page 2014

  74. [74]

    Sophie Giffard-Roisin, Mo Yang, Guillaume Charpiat, Balázs Kégl, and Claire Monteleoni. 2018. Fused deep learning for hurricane track forecast from reanalysis data. In Climate Informatics Workshop Proceedings 2018

    work page 2018

  75. [75]

    Stanley Goldenberg and Lloyd Shapiro. 1996. Physical Mechanisms for the Association of El Nino and West African Rainfall with Atlantic Major Hurricane Activity. Journal of Climate - J CLIMATE 9 (06 1996), 1169–1187

    work page 1996

  76. [76]

    Francesco Granata and Fabio Di Nunno. 2021. Artificial Intelligence models for prediction of the tide level in Venice. Stochastic Environmental Research and Risk Assessment 35, 12 (2021), 2537–2548

    work page 2021

  77. [77]

    Chen Gu, Jifeng Qi, Yizhi Zhao, Wenming Yin, and Shanliang Zhu. 2022. Estimation of the Mixed Layer Depth in the Indian Ocean from Surface Parameters: A Clustering-Neural Network Method. Sensors 22, 15 (2022), 5600

    work page 2022

  78. [78]

    Yanan Guan, Jie Zhang, Xi Zhang, Zhongwei Li, Junmin Meng, Genwang Liu, Meng Bao, and Chenghui Cao. 2021. Identification of Fishing Vessel Types and Analysis of Seasonal Activities in the Northern South China Sea Based on AIS Data: A Case Study of 2018. Remote. Sens. 13, 10 (2021), 1952. J. ACM, Vol. 37, No. 4, Article 111. Publication date: July 2023. 11...

    work page 2021

  79. [79]

    Junting Guo, Jingfang Lu, Yuming Zhang, Chen Zhou, Shufang Zhang, Daosheng Wang, and Xianqing Lv. 2022. Variability of Chlorophyll-a and Secchi Disk Depth (1997–2019) in the Bohai Sea Based on Monthly Cloud-Free Satellite Data Reconstructions. Remote Sensing 14, 3 (2022), 639

    work page 2022

  80. [80]

    Yang Guozhen, Wang Haifeng, Qian Hui, and Fang Jianming. 2017. Tidal current short-term prediction based on support vector regression. InIOP Conference Series: Materials Science and Engineering, Vol. 199. IOP Publishing, 012024

    work page 2017

Showing first 80 references.