Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Neuro-Symbolic Bi-Directional Translation -- Deep Learning Explainability for Climate Tipping Point Research (2306.11161v1)

Published 19 Jun 2023 in cs.LG and cs.AI

Abstract: In recent years, there has been an increase in using deep learning for climate and weather modeling. Though results have been impressive, explainability and interpretability of deep learning models are still a challenge. A third wave of AI, which includes logic and reasoning, has been described as a way to address these issues. Neuro-symbolic AI is a key component of this integration of logic and reasoning with deep learning. In this work we propose a neuro-symbolic approach called Neuro-Symbolic Question-Answer Program Translator, or NS-QAPT, to address explainability and interpretability for deep learning climate simulation, applied to climate tipping point discovery. The NS-QAPT method includes a bidirectional encoder-decoder architecture that translates between domain-specific questions and executable programs used to direct the climate simulation, acting as a bridge between climate scientists and deep learning models. We show early compelling results of this translation method and introduce a domain-specific language and associated executable programs for a commonly known tipping point, the collapse of the Atlantic Meridional Overturning Circulation (AMOC).

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. Bakker, P. 2022. Ocean sensitivity to freshwater. Nature Climate Change, 12(5): 419–420.
  2. Benton, T. G. 2020. Running AMOC in the farming economy. Nature Food, 1(1): 22–23.
  3. The economic impacts of natural disasters: A review of models and empirical studies. Review of Environmental Economics and Policy.
  4. Deep learning for early warning signals of tipping points. Proceedings of the National Academy of Sciences, 118(39): e2106140118.
  5. An Analysis of Deep Neural Network Models for Practical Applications.
  6. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259.
  7. Evidence for sharp increase in the economic damages of extreme natural disasters. Proceedings of the National Academy of Sciences, 116(43): 21450–21455.
  8. Extreme Weather and Climate Change: Population Health and Health System Implications. Annual Review of Public Health, 42(1): 293–315. PMID: 33406378.
  9. Forecasting red tides using an hybrid neuro-symbolic system. AI Communications, 16(4): 221–233.
  10. Neurosymbolic AI: the 3rd wave. arXiv preprint arXiv:2012.05876.
  11. Flux correction and overturning stability: Insights from a dynamical box model. Journal of Climate, 31(22): 9335–9350.
  12. Hysteresis and resilience of the AMOC in an eddy-permitting GCM. Geophysical Research Letters, 45(16): 8547–8556.
  13. Effect of climate change on air quality. Atmospheric Environment, 43(1): 51–63. Atmospheric Environment - Fifty Years of Endeavour.
  14. Revised estimates of the impact of climate change on extreme poverty by 2030.
  15. CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning. In CVPR.
  16. Combined Symbolic-Artificial Neural Net Alarm Processing System. In 11th Power Systems Computation Conference, 259–266.
  17. Welding symbolic AI systems with neural networks and their applications. In 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No. 98CH36227), volume 1, 29–34. IEEE.
  18. ImageNet Classification with Deep Convolutional Neural Networks. In Pereira, F.; Burges, C.; Bottou, L.; and Weinberger, K., eds., Advances in Neural Information Processing Systems, volume 25. Curran Associates, Inc.
  19. What size neural network gives optimal generalization? Convergence properties of backpropagation. Technical report.
  20. Atlantic pycnocline theory scrutinized using a coupled climate model. Geophysical research letters, 37(14).
  21. Rectifier nonlinearities improve neural network acoustic models. In Proc. icml, volume 30, 3. Atlanta, Georgia, USA.
  22. Macukow, B. 2016. Neural Networks – State of Art, Brief History, Basic Models and Architecture. In Saeed, K.; and Homenda, W., eds., Computer Information Systems and Industrial Management, 3–14. Cham: Springer International Publishing. ISBN 978-3-319-45378-1.
  23. The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision.
  24. Modular Neuro-Fuzzy Networks Used in Explicit and Implicit Knowledge Integration. In FLAIRS Conference, 277–281.
  25. The potential effects of climate change on air quality across the conterminous US at 2030 under three Representative Concentration Pathways. Atmospheric chemistry and physics, 18(20): 15471–15489.
  26. FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators.
  27. Deep learning to represent subgrid processes in climate models. Proceedings of the National Academy of Sciences, 115(39): 9684–9689.
  28. Deep learning and process understanding for data-driven Earth system science. Nature, 566(7743): 195–204.
  29. Robinson, W. A. 2021. Climate change and extreme weather: A review focusing on the continental United States. Journal of the Air & Waste Management Association, 71(10): 1186–1209. PMID: 34128774.
  30. Can deep learning beat numerical weather prediction? Philosophical Transactions of the Royal Society A, 379(2194): 20200097.
  31. Deep learning for improved global precipitation in numerical weather prediction systems. arXiv preprint arXiv:2106.12045.
  32. Using Artificial Intelligence to aid Scientific Discovery of Climate Tipping Points.
  33. A Generative Adversarial Network for Climate Tipping Point Discovery (TIP-GAN).
  34. Anomalously weak Labrador Sea convection and Atlantic overturning during the past 150 years. Nature, 556(7700): 227–230.
  35. Velik, R. 2013. Cognitive Architectures as Building Energy Management System for Future Renewable Energy Scenarios. International Journal of Computational Science and Engineering Investigations, 2: 68–72.
  36. Towards automation 2.0: a neurocognitive model for environment recognition, decision-making, and action execution. EURASIP Journal on Embedded Systems, 2011: 1–11.
  37. Williams, R. J. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Reinforcement learning, 5–32.
  38. Clevrer: Collision events for video representation and reasoning. arXiv preprint arXiv:1910.01442.
  39. A normalized Levenshtein distance metric. IEEE transactions on pattern analysis and machine intelligence, 29(6): 1091–1095.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now