Sensor failures are common in tokamak fusion devices, and they cluster precisely when a plasma disruption is approaching, exactly when reliable prediction matters most. Robustness to this kind of failure is one of the key hurdles standing between today's plasma diagnostic ML models and safe, reliable operation in commercial fusion reactors.</p>\n<p>I built a systematic robustness benchmark for plasma diagnostic ML on TokaMark (11,573 MAST tokamak shots), testing XGBoost, LSTM, Transformer, and a CNN baseline across 6 realistic sensor failure scenarios.</p>\n<p>Code, data, and trained checkpoints are all open: github.com/Neerav-Gupta/tokamark-robustness</p>\n","updatedAt":"2026-07-20T19:20:39.993Z","author":{"_id":"66db8fea31e772c5ec513891","avatarUrl":"/avatars/5a5c54f6924d0882da2038b5a982d0a3.svg","fullname":"Neerav Gupta","name":"Neerav-Gupta","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8940770626068115},"editors":["Neerav-Gupta"],"editorAvatarUrls":["/avatars/5a5c54f6924d0882da2038b5a982d0a3.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.11915","authors":[{"_id":"6a5ab4576a69ce099f4d66f9","user":{"_id":"66db8fea31e772c5ec513891","avatarUrl":"/avatars/5a5c54f6924d0882da2038b5a982d0a3.svg","isPro":false,"fullname":"Neerav Gupta","user":"Neerav-Gupta","type":"user","name":"Neerav-Gupta"},"name":"Neerav Gupta","status":"claimed_verified","statusLastChangedAt":"2026-07-20T16:05:52.580Z","hidden":false}],"publishedAt":"2026-07-05T00:00:00.000Z","submittedOnDailyAt":"2026-07-20T00:00:00.000Z","title":"Benchmarking Sensor Robustness in Plasma Diagnostic Models: A Systematic Evaluation on TokaMark","submittedOnDailyBy":{"_id":"66db8fea31e772c5ec513891","avatarUrl":"/avatars/5a5c54f6924d0882da2038b5a982d0a3.svg","isPro":false,"fullname":"Neerav Gupta","user":"Neerav-Gupta","type":"user","name":"Neerav-Gupta"},"summary":"Plasma diagnostic models for tokamak fusion devices are almost universally evaluated on clean, complete sensor data. In practice, fusion diagnostics fail regularly: acquisition systems start late, individual sensors die, and signal dropouts cluster precisely when a plasma disruption is approaching. We present the first systematic robustness benchmark for plasma diagnostic ML using the TokaMark dataset of 11,573 MAST shots, evaluating XGBoost, LSTM, Transformer, and the TokaMark CNN baseline across six physically-grounded failure scenarios and three imputation strategies. We introduce the Robustness Score (RS) for standardized cross-architecture comparison. Our central finding is that disruption-proximate sensor failure (corruption injected in the final window timesteps) collapses sequence model performance (LSTM +212% NRMSE) while a statistical feature model remains comparatively stable (XGBoost +37%). Forward-fill imputation eliminates nearly all degradation from random dropout for sequence models (LSTM +57% to ~0%), but offers little help when the end of the window is corrupted. Shot-level alarm evaluation using ground-truth disruption timestamps reveals that LSTM alarm detection collapses to TPR=0.00 under proximate sensor failure, while mean-fill imputation recovers it to TPR=1.00, a reversal of the pattern observed in NRMSE. Plasma current emerges as the single most critical diagnostic across all architectures (+73% to +140% upon removal). Code, data, and trained checkpoints are available at https://github.com/Neerav-Gupta/tokamark-robustness.","upvotes":0,"discussionId":"6a5ab4576a69ce099f4d66fa","githubRepo":"https://github.com/Neerav-Gupta/tokamark-robustness","githubRepoAddedBy":"user","githubStars":3},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[],"acceptLanguages":["en"],"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2607/2607.11915.md","query":{}}">
Benchmarking Sensor Robustness in Plasma Diagnostic Models: A Systematic Evaluation on TokaMark
Abstract
Plasma diagnostic models for tokamak fusion devices are almost universally evaluated on clean, complete sensor data. In practice, fusion diagnostics fail regularly: acquisition systems start late, individual sensors die, and signal dropouts cluster precisely when a plasma disruption is approaching. We present the first systematic robustness benchmark for plasma diagnostic ML using the TokaMark dataset of 11,573 MAST shots, evaluating XGBoost, LSTM, Transformer, and the TokaMark CNN baseline across six physically-grounded failure scenarios and three imputation strategies. We introduce the Robustness Score (RS) for standardized cross-architecture comparison. Our central finding is that disruption-proximate sensor failure (corruption injected in the final window timesteps) collapses sequence model performance (LSTM +212% NRMSE) while a statistical feature model remains comparatively stable (XGBoost +37%). Forward-fill imputation eliminates nearly all degradation from random dropout for sequence models (LSTM +57% to ~0%), but offers little help when the end of the window is corrupted. Shot-level alarm evaluation using ground-truth disruption timestamps reveals that LSTM alarm detection collapses to TPR=0.00 under proximate sensor failure, while mean-fill imputation recovers it to TPR=1.00, a reversal of the pattern observed in NRMSE. Plasma current emerges as the single most critical diagnostic across all architectures (+73% to +140% upon removal). Code, data, and trained checkpoints are available at https://github.com/Neerav-Gupta/tokamark-robustness.
Community
Sensor failures are common in tokamak fusion devices, and they cluster precisely when a plasma disruption is approaching, exactly when reliable prediction matters most. Robustness to this kind of failure is one of the key hurdles standing between today's plasma diagnostic ML models and safe, reliable operation in commercial fusion reactors.
I built a systematic robustness benchmark for plasma diagnostic ML on TokaMark (11,573 MAST tokamak shots), testing XGBoost, LSTM, Transformer, and a CNN baseline across 6 realistic sensor failure scenarios.
Code, data, and trained checkpoints are all open: github.com/Neerav-Gupta/tokamark-robustness
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2607.11915 in a model README.md to link it from this page.
Cite arxiv.org/abs/2607.11915 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.