---
title: 'PhyDAE: Physics-Guided Degradation-Adaptive Experts'
url: https://www.emergentmind.com/topics/physics-guided-degradation-adaptive-experts-phydae
type: topic
---

# PhyDAE: Physics-Guided Degradation-Adaptive Experts

Searching arXiv for PhyDAE and closely related physics-guided degradation-adaptive battery methods.
Physics-Guided Degradation-Adaptive Experts (PhyDAE) denotes a modeling paradigm in which degradation is elevated from an implicit nuisance factor to an explicit control or routing signal, and expert specialization is constrained by domain physics. In its exact arXiv usage, PhyDAE is the remote sensing image restoration framework introduced in "PhyDAE: Physics-Guided Degradation-Adaptive Experts for All-in-One Remote Sensing Image Restoration" [2510.08653]. In a broader interpretive sense, closely related ideas appear in battery research that couples degradation estimation, physics-guided representation, and adaptive expert or policy selection, including physics-informed reinforcement learning for charging [2510.11515], physics-guided test-time adaptation for state-of-health estimation [2402.00068], and the Physics-Informed Mixture of Experts network for second-life degradation trajectory computation [2506.17755]. This suggests that PhyDAE can be understood both as a specific architecture and as a more general design philosophy spanning restoration, forecasting, and control.

## 1. Definition and scope

The exact PhyDAE formulation targets **all-in-one remote sensing image restoration** under multiple heterogeneous degradations, specifically **haze, noise, blur, and low-light conditions**. Its central claim is that existing all-in-one restoration methods rely excessively on implicit feature representations and lack explicit modeling of degradation physics, whereas PhyDAE transforms degradation information from implicit features into explicit decision signals through a **two-stage cascaded architecture**, **progressive degradation mining**, and **physics-aware expert modules** [2510.08653].

A broader, inferential use of the term is supported by contemporaneous battery work. The charging framework in "A Physics-Informed Reinforcement Learning Approach for Degradation-Aware Long-Term Charging Optimization in Batteries" does not use the PhyDAE name, but it explicitly estimates **Loss of Active Material (LAM)** and adapts the **CCCV constant-current stage** over the battery lifetime, which aligns with the degradation-adaptive, physics-guided aspect of the concept [2510.11515]. Likewise, the second-life battery paper "Physics-informed mixture of experts network for interpretable battery degradation trajectory computation amid second-life complexities" uses sparse expert routing based on physics-informed signals and is explicitly framed as PhyDAE-style modeling in the supplied material [2506.17755]. By contrast, "Adapting Amidst Degradation: Cross Domain Li-ion Battery Health Estimation via Physics-Guided Test-Time Training" is not a PhyDAE paper, and its physics guidance is described as limited in the supplied text, but it still exemplifies continual adaptation amidst degradation [2402.00068].

| Work | Domain | Degradation-adaptive mechanism |
|---|---|---|
| [2510.08653] | Remote sensing restoration | Residual-guided physics-aware experts with sparse routing |
| [2510.11515] | Battery charging control | LAM estimation and adaptive CCCV constant-current selection |
| [2506.17755] | Second-life battery forecasting | Physics-informed mixture of experts plus recurrent trajectory prediction |
| [2402.00068] | Battery SOH estimation | Continual test-time adaptation with reconstruction self-supervision |

The common thread is not merely the presence of physics priors or experts in isolation. Rather, the defining structure is that degradation is explicitly inferred, represented, and then used to modulate downstream prediction, restoration, or control.

## 2. Progressive degradation mining and explicit decision signals

In the exact PhyDAE architecture, restoration is organized as a **two-stage cascaded design**. A first-stage encoder-decoder generates a coarse restoration,
\[
\hat{\mathbf{x}}_0 = \mathcal{G}^{(0)}(\mathbf{y}),
\]
after which the residual
\[
\mathbf{r}_0 = \mathbf{y} - \hat{\mathbf{x}}_0
\]
is analyzed rather than discarded [2510.08653]. The second stage refines the result by conditioning on residual-derived degradation cues:
\[
\hat{\mathbf{x}} = \mathcal{G}^{(1)}\left(\mathbf{y}\mid \mathcal{M}_{\mathrm{RMP}}(\mathbf{r}_0), \mathcal{F}_{\mathrm{FADD}}(\mathbf{r}_0), \boldsymbol{\pi}_{\mathrm{deg}}\right).
\]

Two modules are responsible for converting residual evidence into structured guidance. The **Residual Manifold Projector (RMP)** interprets residuals through manifold geometry, producing multi-scale residual embeddings. The **Frequency-Aware Degradation Decomposer (FADD)** analyzes residuals in the frequency domain with \(7\times7\), \(5\times5\), \(3\times3\), and \(1\times1\) kernels corresponding to low-, mid-, high-frequency, and edge or pixel-wise responses. These signals are fused into a degradation posterior,
\[
\boldsymbol{\pi}_{\text{deg}} = \operatorname{Softmax}\left(\operatorname{Linear}\left(\operatorname{Flatten}\left(\operatorname{AdaptivePool}(\mathbf{R}_1)\right)\right)\right),
\]
which is a 4-class distribution over haze, noise, low-light, and blur [2510.08653].

This conversion from residuals to explicit routing signals is the conceptual center of PhyDAE. The paper’s claim is that direct end-to-end restoration is unstable and inefficient when the network must simultaneously identify degradation type, estimate severity, and reconstruct the clean scene. Progressive degradation mining separates these functions: coarse correction first, degradation analysis second, expert refinement last. A plausible implication is that this staged factorization is what makes the term “degradation-adaptive” more precise than generic conditional restoration.

## 3. Expert specialization and sparse routing

PhyDAE’s experts are not generic subnetworks. They are tied to degradation-specific physical models. The **dehazing expert** is based on atmospheric scattering,
\[
\mathbf{I}(\mathbf{p}) = \mathbf{J}(\mathbf{p}) \odot \mathbf{t}(\mathbf{p}) + \mathbf{A} \odot (1-\mathbf{t}(\mathbf{p})),
\]
with channel-wise transmittance and mixed global-local atmospheric light estimation. The **denoising expert** assumes spatially varying noise and uses a three-tier adaptive filtering strategy. The **low-light expert** is grounded in Retinex-style illumination-reflectance separation. The **deblurring expert** uses anisotropic Gaussian degradation with directional weighting derived from \(\sigma_x\), \(\sigma_y\), and \(\theta\) [2510.08653].

Routing is performed by a **temperature-controlled sparse activation strategy**. Visual, frequency, and degradation-prior cues are fused into logits \(\ell\), followed by
\[
\mathbf{w}_{\text{route}} = \operatorname{Softmax}\left(\frac{\ell}{\tau}\right),
\]
and Top-\(K\) selection,
\[
(\mathbf{w}_{\text{top}}, \mathbf{I}_{\text{top}})=\operatorname{TopK}(\mathbf{w}_{\text{route}}, K).
\]
The paper uses **4 experts** and **Top-K routing with \(k=1\) for efficiency** [2510.08653]. Lower \(\tau\) sharpens routing, whereas higher \(\tau\) softens it.

A structurally analogous but domain-shifted formulation appears in PIMOE for second-life batteries. Its **Adaptive Multi-degradation Prediction (AMDP)** module defines the latent degradation trend as
\[
Trend_i = \sum_{j=1}^{N_{expert}} G_j(F_i)\cdot Expert_j(q_i),
\]
where routing weights are produced by a noisy sparse gate,
\[
g(F_i)= Softmax(Softmax(TopK(H(F_i), k))).
\]
That model uses **5 experts** with **TopK = 2**, and regularizes batch-averaged expert usage through
\[
L_{router} = \frac{Var(A_1, A_2, \ldots, A_E)} {(Mean(A_1, A_2, \ldots, A_E))^2 + \epsilon}
\]
to prevent expert collapse [2506.17755].

The parallel is exact at the level of mechanism: degradation-sensitive features are transformed into sparse expert allocations. The domains differ sharply, but the architectural logic is shared.

## 4. Battery realizations of degradation-adaptive physics guidance

In long-term charging optimization, the physics-informed RL framework addresses a specific weakness of the ubiquitous **CCCV** protocol: the **constant-current phase** is typically fixed even as degradation accumulates. The charging cycle is modeled as a standard CCCV process from \(2.5\ \text{V}\) to \(4.2\ \text{V}\), ending when the CV current falls to **0.1 A**. Each RL step corresponds to **one full charge cycle**, and the controller chooses the **magnitude of the constant-current part** of CCCV for the next cycle [2510.11515].

The method uses **PyBaMM** as the battery “truth model,” **Stable-Baselines3** for implementation, and a **PPO** agent. The environment is based on the **Doyle-Fuller-Newman (DFN)** model, while the reward includes a reduced-order **Single Particle Model (SPM)** reference voltage. The RL state is
\[
s = \{ V_{cell},\ Q,\ C_{rate},\ \epsilon_s^+ \},
\]
and the action is
\[
a = \{ \Delta C_{rate},\ \Delta \epsilon_s^+ \},
\]
so the agent both adjusts the next-cycle CC rate and updates an internal estimate of the **cathode active material volume fraction** \(\epsilon_s^+\), which represents LAM. The reward is
\[
r = \alpha_1 r_1 + \alpha_2 r_2 + \alpha_3 r_3,
\]
with a degradation safeguard penalty of 500 when
\[
\epsilon_s^+ < 0.7 \epsilon_0^+ .
\]
Episodes are trained over **100 cycles** [2510.11515].

PIMOE addresses a different battery problem: computing degradation trajectories for retired cells under second-life uncertainty from **single-cycle partial data**. It uses a **partial charging curve** from a random initial SOC to cutoff voltage, a **30-minute relaxation voltage curve**, and future operation inputs consisting of **charge current, discharge current, temperature**. From these signals it extracts **12 normalized features**—**6 from relaxation voltage** and **6 from capacity-voltage curves**—including the specially designed \(Q_{0.05}\) and \(AV_{200}\), then feeds the latent trend embedding into the **Future-Operation Recurrent Neural Network (FORNN)** for long-horizon trajectory prediction [2506.17755].

BatteryTTT occupies a third position. It is a **two-head Y-shaped architecture** with shared feature extractor \(f\), regression head \(h\), and self-supervised head \(g\). The adaptation pipeline has **joint pre-training**, **fine-tuning using the first cycle** with SOH \(=1\), and **self-supervised test-time training** in which each new unlabeled sample updates \(f\) and \(g\) while \(h\) remains frozen. The supplied text explicitly notes that this paper does **not** contain rich physics-guided battery constraints such as monotonic capacity fade or conservation-law regularizers; its adaptation signal is instead a **reconstruction loss** on charging curves [2402.00068]. This makes it adjacent to PhyDAE in degradation adaptivity, but not identical in its use of physics.

## 5. Empirical results and reported operating regimes

The exact PhyDAE paper evaluates on **MD-RSID**, **MD-RRSHID**, and **MDRS-Landsat**. On MD-RSID it reports **26.86 PSNR / 0.9613 SSIM / 0.0586 LPIPS** for dehazing, **27.73 / 0.7772 / 0.3221** for deblurring, **32.77 / 0.8862 / 0.2136** for denoising, and **31.96 / 0.9855 / 0.0211** for low-light enhancement. On MD-RRSHID it reports **22.96 / 0.6511 / 0.4423** for dehazing, **33.73 / 0.8787 / 0.2122** for deblurring, **35.17 / 0.9141 / 0.2289** for denoising, and **37.35 / 0.9852 / 0.0442** for low-light. On MDRS-Landsat it reports **39.12 / 0.9928 / 0.0227**, **36.88 / 0.8824 / 0.1487**, **34.53 / 0.8651 / 0.0991**, and **42.24 / 0.9949 / 0.0121** for the same four tasks. The reported model complexity is **17.21M parameters**, **65.66 MB memory**, and **71.63 GFLOPs**, with an average cross-domain retention rate of **76.41%** [2510.08653].

For second-life battery trajectory computation, PIMOE is validated on **207 batteries** across **77 use conditions** and **67,902 cycles**. The abstract reports **average MAPE = 0.88%** and **inference time = 0.43 ms per battery**. It further reports **150-cycle forecasts** with **1.50% average** and **6.26% maximum MAPE**, and continued operation with pruned **5 MB** training data [2506.17755].

For degradation-aware charging, the PPO-based method compares three schemes after **100 cycles**: **proposed physics-informed RL** with **8.54%** capacity fade, **fixed CCCV** with **9.61%**, and **RL without LAM estimate** with **10.34%**. The reported qualitative behavior is that the learned policy **reduces the charging C-rate as the battery aged**, which increases charging time somewhat but reduces degradation accumulation [2510.11515].

For cross-domain SOH estimation, GPT4Battery reports **average MAE = 2.17%** in the zero-shot setting, compared with **3.87%** for Benchmark1 and **2.97%** for Benchmark2, while **swarm** attains **1.55%** under a domain adaptation setting where target data is accessible. The paper also reports **0.87%** on SANYO, **0.81%** on PANASONIC, **1.43%** on CALCE, and **5.56%** on KOKAM [2402.00068].

These results indicate that the PhyDAE pattern is empirically instantiated in at least three forms: restoration quality with efficient sparse experts, history-free degradation trajectory forecasting, and degradation-aware control.

## 6. Conceptual boundaries, limitations, and common misconceptions

A first misconception is to treat PhyDAE as synonymous with any mixture-of-experts model. The supplied literature does not support that equivalence. In the exact named method, PhyDAE is a remote sensing restoration framework with residual-guided degradation analysis, physics-aware expert modules, and composite losses including **DAOT**, **adaptive pixel loss**, **expert balance loss**, and **contrastive loss** [2510.08653]. The charging paper, by contrast, is framed as a **single PPO-based RL policy** rather than an ensemble of experts, and the supplied text explicitly states that it does not use a mixture-of-experts architecture or the PhyDAE name [2510.11515].

A second misconception is that “physics-guided” implies fully mechanistic end-to-end modeling. The literature is more heterogeneous. The charging paper anchors learning with **DFN** and **SPM** structure and a degradation variable \(\epsilon_s^+\) representing LAM [2510.11515]. PIMOE uses physics-informed macroscopic signals such as capacity-voltage and relaxation voltage, but the paper notes that its “physics” is still **largely statistical rather than deeply mechanistic** [2506.17755]. BatteryTTT goes further in that direction: the supplied text states plainly that it does **not** provide explicit lithium-ion constraints such as monotonic fade or conservation laws, and instead uses self-supervised reconstruction [2402.00068].

A third misconception is that degradation adaptivity is automatically comprehensive. In the charging paper, the degradation signal is represented mainly by **cathode active material fraction / LAM**, so it is not a full multi-degradation expert [2510.11515]. In PIMOE, future operating conditions are assumed available, and the datasets do not fully cover **thermal runaway**, **internal short circuits**, or **highly non-stationary and extreme operating environments** [2506.17755]. In remote sensing PhyDAE, the reported cross-domain retention rate of **76.41%** indicates nontrivial generalization, but not immunity to domain shift [2510.08653].

Taken together, these limitations clarify the most defensible interpretation of PhyDAE. It is best understood as a structured strategy for combining degradation inference, physics-guided representation, and adaptive specialization. The exact implementation varies from residual-guided sparse experts in image restoration to LAM-aware PPO control and second-life degradation routing in batteries, but the unifying principle is consistent: degradation is explicitly modeled and then used to condition differentiated processing rather than absorbed into a single undifferentiated black box.

Source: https://www.emergentmind.com/topics/physics-guided-degradation-adaptive-experts-phydae