wikillm

Paper · 2026-10-31 · cs.LG

Generative Forecasting from Coarse Observations: Does Cascading Help?

Builds reference ensembles of the true conditional forecast for five PDE systems by simulating many fine-scale completions per coarse state. Direct diffusion and stochastic-interpolant forecasters miss the conditional distribution. Chaining learned shorter transitions cuts csFID-10k 2.3 to 5.7x on four systems but hurts a Gaussian passive scalar.

Diffusion modelsDirect multi-step forecastingGenerative model evaluationFréchet Inception Distance (FID)forecastinggenerative-modelsstochastic-interpolantspde-surrogatesevaluation

arXivPDFCodeMarkdown13 min read

AI-compiled by claude-haiku-5-5 on 2026-11-21, not yet reviewed by a human. Every claim cites its source; check it when a detail matters.

In plain words

Weather and fluid models predict a future from a blurry snapshot of the present. The fine details that were lost in the blur still shape what happens next, so the same snapshot can lead to many different futures. A good forecaster should give the spread of those futures, not just one plausible-looking picture.

Checking this is hard, because a real simulation only ever shows one future per snapshot. The authors get around that by running the simulator many times from the same blurry snapshot, each time with different hidden details. That gives a reference cloud of possible futures to compare against.

With that reference, they find that standard generative forecasters can produce convincing single pictures whose average and spread are wrong. Their remedy is to split the forecast into several shorter steps, learn each step, and chain them. That helps for most of the test systems, and hurts for one simple linear system where the direct forecast is already easy to learn. A small analytic model explains why there is a best number of steps in between.

TL;DR

  • Builds a benchmark of five 2D physical systems. Each test observation has 10,000 simulator-generated reference futures §2 §4 app. B.1.
  • Direct stochastic interpolant (SI) and EDM forecasters can produce plausible samples with the wrong conditional mean and spread §2 fig. 2.
  • Cascaded SI with a validation-selected depth lowers test csFID-10k on Euler, SQG, heterogeneous waves and nonlinear Klein-Gordon. It is worse on the passive scalar, where the validation-selected depth is 1 §5 tab. 2.
  • Author-reported, one training seed, 10 test observations. The gains depend on a fixed budget of 16,000 supervised pairs and on the sampler cost of depth S §4 app. B.2.

Problem

A forecaster sees only a coarse state X_0 of a system, and the target is the conditional law P(X_T | X_0 = x_0) §2 (eq. 2.1). The unseen fine scales differ between full states that share x_0, so one observation can lead to many futures §2.

Ordinary trajectory data contain one future per initial state, so they can rank forecasters but cannot measure the distance to the true conditional law §2. The paper therefore builds reference ensembles by sampling many fine-scale completions per coarse state and evolving each with a solver §2 (eq. 2.3) fig. 1.

Direct forecasters learn P(X_T | X_0) from endpoint pairs alone. Learning a long transition in one go may be hard for a model of limited capacity, and composing short transitions loses information when the observed process is not Markov, because the unresolved scales carry memory §3.

Method

Benchmark construction §2 §4 app. B.1. For each of 80 training, 10 validation and 10 test observations, the authors simulate an ensemble of trajectories that share the observed state and differ in hidden components. Each training ensemble stores 200 trajectories at 41 equally spaced times. Each test ensemble has 10,000 endpoints. Observations keep Fourier modes with 0 < |k| <= 8, which gives 196 real coordinates per field §2 tab. 3.

Forecasters §4 app. B.2.

  • Direct SI: one stochastic interpolant from X_0 to X_T, trained on endpoint pairs §4.
  • Cascaded SI: one SI network shared by all transitions, conditioned on the physical start and end times. A depth-S forecast applies S learned transitions in sequence §3 (eq. 3.1) §4.
  • EDM: a conditional diffusion model with the same endpoint training pairs as Direct SI §4 app. B.2.

Stochastic interpolant objective app. B.2. For a normalised pair (a, b), with auxiliary time tau uniform on [0, 1], Gaussian z, and noise scale sigma, the interpolant and regression target are

I_\tau = (1-\tau)\,a + \tau\,b + \sigma(1-\tau)\sqrt{\tau}\,z, \qquad R_\tau = b - a - \sigma\sqrt{\tau}\,z app. B.2

The drift b_theta regresses R_tau from (I_tau, tau, a, t_i, t_{i+1}). The loss averages the sum of one half of the squared drift minus the drift times R_tau over the antithetic draws z and -z app. B.2.

Sampling app. B.2. Each segment is integrated with Euler-Maruyama in auxiliary time, starting from the segment's start state a:

dZ_\tau = b_\theta(Z_\tau, \tau, a, t_i, t_{i+1})\,d\tau + \sigma(1-\tau)\,dW_\tau, \qquad Z_0 = a app. B.2

In a cascade, the endpoint of one segment becomes the start state of the next app. B.2 §3.

Pseudocode
# Stochastic-interpolant loss for one segment  [app. B.2]
# Input:  a, b (normalised, (batch, D)); sigma (noise scale)
# Output: scalar loss

def si_loss(a, b, sigma):
    # draw auxiliary time and Gaussian noise  [app. B.2]
    tau = uniform(0, 1, size=batch)                 # (batch,)
    z = gaussian_like(a)                            # (batch, D)
    loss = 0
    # antithetic pair: evaluate the same draw at +z and -z  [app. B.2]
    for eps in (z, -z):
        # interpolant at this noise draw  [app. B.2]
        state = (1 - tau) * a + tau * b
        state = state + sigma * (1 - tau) * sqrt(tau) * eps
        # regression target, sign of eps flips with it  [app. B.2]
        target = b - a - sigma * sqrt(tau) * eps
        drift = network(state, tau, a, t_start, t_end)
        loss = loss + 0.5 * sum(drift ** 2) - sum(drift * target)
    return loss
Pseudocode
# Cascaded forecast of depth S  [§3] [eq. 3.1]
# Input:  observed state x0, depth S, horizon T, learned SI drift
# Output: one sample of the forecast X_T

def cascaded_forecast(x0, S, T, drift):
    # each segment is sampled from the endpoint of the previous one  [§3]
    state = x0
    for i in range(S):
        t_start = i * T / S
        t_end = (i + 1) * T / S
        # Euler-Maruyama over auxiliary time for this segment  [app. B.2]
        state = sample_segment(state, t_start, t_end, drift)
    return state

Rotation-OU analytic model §3 (eqs. 3.2, 3.3). A two-dimensional state Y_t rotates at a speed set by omega and an observed variable c, where c is drawn uniformly from [-1, 1]. It is also driven by a hidden Ornstein-Uhlenbeck process H_t. The paper uses the following SDE, with J the 2x2 rotation generator and R(theta) the rotation by theta:

dH_t = -\kappa H_t\,dt + \sqrt{2\kappa}\,dB_t, \qquad dY_t = \bigl(\omega c J Y_t + \beta_\rho R(\omega c t) H_t\bigr)dt + \sigma_\rho\,dW_t §3 (eq. 3.2)

With a fixed q > 0 and 0 <= rho < 1, the target conditional at time T is the Gaussian

Y_T \mid (Y_0 = y, c) \sim \mathcal N\bigl(R(\omega c T)\,y,\; q I_2\bigr) §3 (eq. 3.3)

The target does not depend on rho. rho sets how much of the endpoint variance comes from the hidden process §3.

Metric §4 (eq. 4.1), app. B.3. The reference and generated endpoints each give a mean and covariance of a feature map phi. Their Frechet distance is

d_e = \lVert m_e - \widehat m_e \rVert^2 + \operatorname{tr}\Bigl[C_e + \widehat C_e - 2\bigl(C_e^{1/2}\widehat C_e C_e^{1/2}\bigr)^{1/2}\Bigr] §4 (eq. 4.1)

csFID-10k averages d_e over the ten test observations. The features are spatial Inception activations, see Hyperparameters and Pitfalls. The paper also reports pooled cFID and a state-space energy distance for diagnostics app. B.4.

Hyperparameters

Values as stated in the paper unless marked. Selected configurations are frozen after validation selection app. B.2 tab. 6.

NameValueWhereNotes
Training pairs budget B16,000§4 app. B.2Direct SI and EDM take one pair per trajectory; a depth-S cascade takes every transition from 200/S trajectories per ensemble
Optimizer updates30,000§4 app. B.2Adam, batch 256, constant LR, no weight decay
Adam betas, eps(0.9, 0.999), 1e-8app. B.2float32, no TF32 or mixed precision
EMAhalf-life 500,000 examples; ramp-up ratio 0.05app. B.2used for validation and test
Checkpoint scoringevery 1,000 updates, plus 100, 200, 300, 500, 750app. B.2
LR grid{1e-4, 3e-4, 1e-3}, then boundary extensionapp. B.2extension {3e-5, 1e-5} or {3e-3, 1e-2}
SI noise scale grid{0.25, 0.5, 1, 2, 4, 8, 16, 32}, then boundary extensionapp. B.2extension {0.125, 0.0625} or {64, 128}
EDM P_mean grid{-3.2, -2.8, ..., -0.4}, then extensionapp. B.2sigma_data 1, P_std 1.2
EDM samplerHeun, sigma_min 0.002, sigma_max 80, exponent 7app. B.2n steps cost 2n - 1 network evaluations
SI gradient clippingnorm 1app. B.2EDM uses no clipping and no LR ramp-up
U-Netwidths 64, 128, 256; circular 3x3 conv; SiLU; two average-pool stages; skip connectionsapp. B.2acts on a 32x32 reconstruction of observed modes
Euler U-Net parameters1,515,265app. B.2
Cascade depths searchedS in {1, 2, 5, 10, 20, 40}§4 app. B.2selected on validation by energy distance
Sampler resolution ladder20, 40, 80, 160, 320, 640 stepsapp. B.2first doubling with under 5% change
Selected configuration: EulerDirect SI: lr 1e-4, sigma 8, 5,000 updates, 40 steps. Cascaded S=10: lr 3e-4, sigma 8, 17,000 updates, 80 steps per segment (NFE 800)tab. 6
Selected configuration: SQGDirect SI: lr 1e-4, sigma 16, 4,000 updates. Cascaded S=10: lr 1e-3, sigma 16, 11,000 updates, 160 steps per segment (NFE 1600)tab. 6
Selected configuration: wavesDirect SI: lr 1e-3, sigma 32, 6,000 updates. EDM: lr 3e-5, P_mean -0.4. Cascaded S=5: lr 3e-3, sigma 2, 30,000 updates, 40 steps per segment (NFE 200)tab. 6
Selected configuration: Klein-GordonDirect SI: lr 1e-3, sigma 128, 15,000 updates. Cascaded S=20: lr 1e-4, sigma 1, 30,000 updates, 320 steps per segment (NFE 6400)tab. 6
Selected configuration: passive scalarDirect and Cascaded SI (same model, S=1): lr 3e-3, sigma 1, 6,000 updates, 40 steps. EDM: lr 1e-3, P_mean -1.2, 16,000 updatestab. 6
Evaluation samples10,000 generated and 10,000 reference per test observation§4 app. B.3
csFID preprocessing128x128 reconstruction; clip at training 0.9999 quantile ofamplitude; 3 identical channels; bicubic resize to 299x299
csFID featuresfirst 7 channels of Inception mixed_6/conv (17x17), flattened, 2023 featuresapp. B.3no spatial pooling
Dataset grids and horizonsEuler 1024^2, T=1; SQG 256^2, T=20; waves 512^2, T=1; Klein-Gordon 128^2, T=12; passive scalar 512^2, T=1tab. 3horizons in physical time; 41 snapshots each
Euler solverazeban pseudospectral, 1024^2, SSP-RK3, CFL 0.5, smooth-cutoff spectral viscosity s=1, eps=0.4app. B.1
Passive-scalar diffusivitykappa = 6.184154e-6; K = 2; V = 0.5app. B.1

Results

Author-reported. Setup: five systems, ten test observations, one training seed, csFID-10k (lower is better), mean with SEM over test observations §5 tab. 2. The depth S* is chosen on validation data §5.

SystemDirect SIEDMCascaded SIS*Source
Euler57.26 ± 3.3556.32 ± 3.7416.32 ± 1.1410tab. 2
SQG138.48 ± 23.09118.62 ± 21.6751.24 ± 8.3210tab. 2
Heterogeneous waves115.86 ± 6.76123.04 ± 7.0736.66 ± 1.785tab. 2
Nonlinear Klein-Gordon98.48 ± 6.1892.37 ± 5.4316.24 ± 1.5520tab. 2
Passive scalar8.67 ± 0.287.88 ± 0.318.67 ± 0.281tab. 2

Derived from the table, relative to the better direct forecaster: Euler about 3.5x (against both direct methods), SQG 2.3x, Klein-Gordon 5.7x, waves more than 3x against both §5 tab. 2.

Depth sweep, test csFID-10k app. B.6 tab. 7. Cascaded SI error versus S:

SEulerSQGWavesKlein-GordonPassive scalar
1 (Direct SI)57.26138.48115.8698.488.67
253.6083.2571.2399.7518.75
522.9443.5736.6653.1032.97
1016.3251.2444.5122.5041.14
2017.8689.0858.2816.2456.95
4023.2986.9862.8118.2375.21
EDM56.32118.62123.0492.377.88

Other results, all author-reported app. B.6:

  • Training with 16,000 distinct initial conditions and one trajectory each, Euler: Direct SI 44.20 ± 3.29, Cascaded S=10 14.70 ± 0.48 tab. 11.
  • Euler with 800 initial conditions x 20 trajectories for Direct SI: 49.11 ± 3.52, against 59.88 ± 3.39 at 80 x 200; Cascaded S=10 at 80 x 20 x 10: 16.63 ± 0.81 tab. 10.
  • Euler horizon study (three training seeds): Direct SI versus Cascaded SI with selected depth goes 41.3 vs 19.2 at T=0.2, and 59.8 vs 16.6 at T=1.0 tab. 13.
  • Anchored cascade (conditioning every stage on X_0): on passive scalar it reduces error at every depth S >= 2, e.g. 41.14 to 26.00 at S=10. On Euler it gives no gain at any depth app. B.6 tab. 14.
  • Dependent-prior SQG variant: Cascaded SI 53.18 ± 15.63 at S*=5, against Direct SI 141.93 ± 23.46 app. B.6.
  • Euler diagnostic metrics at S*=10 tab. 8: cFID 8.96 (Cascaded) versus 24.30 (Direct) and 14.94 (EDM). csFID alone is nearly tied for Direct and EDM (difference -0.94 ± 0.90).
  • Rotation-OU model §3 app. C: for rho = 0 the error decays as O(S^-2). For fixed 0 < rho < 1 it is C_{rho,inf} - Lambda_rho T/S + O(S^-2), so a finite optimal depth S* >= 2 exists for small rho. The paper also proves that rho^2 S*(rho) converges to a constant as rho goes to 0.

Paper vs code

Checked against the authors' code repository on Hugging Face, linked from the paper's data availability statement §6. This is not a GitHub repository, so it could not be cloned. Files were read through the web interface. Line numbers are not available, so code citations here give file paths only. Code licence: MIT (code/LICENSE). The code was not run.

  • Loss and sampler structure: consistent. The Cascaded SI loss uses an antithetic pair z and -z, with the one-half-squared-norm minus dot-product form, tau uniform on the unit interval, and the sigma(1 - tau) sqrt(tau) interpolant noise and -sigma sqrt(tau) target noise. The sampler adds sigma(1 - tau) noise per step, and a segment's start is the previous endpoint core.py app. B.2 §3.
  • Euler cascade training config: consistent with the paper. Learning rate 3e-4, batch 256, 30,000 updates, sigma_train 8.0, U-Net base channels 64, 32x32 grid, 196 observed coordinates, EMA half-life 500 k-images with ramp 0.05, gradient clipping at norm 1.0, shared network conditioned on segment start and end times config.yaml tab. 6 app. B.2.
  • Sampler steps: not reconciled. The released S=10 Euler config sets 20 SDE steps per segment and evaluates with noise scale 1.0 config.yaml. The paper's Table 6 reports 80 steps per segment (NFE 800) for the same configuration tab. 6. The paper says sampler resolution is calibrated separately, so the released config may not be the reported setting. Not resolved here.
  • Direct SI and EDM configs: not checked. The Direct SI run folder listed as cascaded_si_S01 was not opened. The EDM and waves, SQG, Klein-Gordon and passive-scalar configs were not read.
  • Anchoring, dependent prior, and wave velocity proxy: not checked in code. The code's comments describe the segment start as the anchor. This is a different quantity from the paper's anchor X_0 app. B.6 core.py.
  • Licence statements disagree in form. The arXiv record says CC BY 4.0, the Hugging Face model card says cc-by-4.0, and the code licence is MIT. The dataset page shows no licence. This card publishes no data or model weights.
  • Code README still refers to an anonymous submission. The README calls the repository reproduction code for the "anonymous submission". The arXiv record names authors, so the code reflects an earlier version of the paper README.md.
  • Commit. code_commit is the newest commit of the Hugging Face repository (1a2de03, "Update code/README.md"), read from the commit list. The commit list does not filter by path, so it is not verified that this commit changed only code/.

Searched for an official repository: the paper's data availability statement links the Hugging Face organisation coarse-grained-forecasting-benchmark. No GitHub search was run because the link is in the paper.

Pitfalls

  • Validation-selected depth is not always the test optimum. On SQG, the test optimum among the depths shown is S=5 (43.57 ± 8.79), while validation selects S=10 (51.24 ± 8.32) tab. 7. The paper reports both.
  • Passive scalar: EDM is best, and cascading hurts. With S*=1 the Cascaded and Direct SI models are the same fitted model. EDM is 7.88 ± 0.31 against 8.67 ± 0.28. Every added stage raises error, to 75.21 at S=40 §5 tab. 7.
  • Fixed pair budget is deliberate and harsh. Each cascade of depth S sees only 200/S trajectories per ensemble, so the cascade uses fewer distinct initial conditions. The paper says this is a harsh constraint and that the intermediate observations are often available in practice §4. Results may change if all intermediate states are used.
  • Compute cost scales with S. Euler Cascaded S=10 uses 800 network evaluations against 40 for Direct SI. Matched-cost re-evaluation improved Direct SI by only 1-2% on waves and Klein-Gordon tab. 5 app. B.2. A cost-matched comparison is the right baseline when budgets differ.
  • Single training seed. The main table reports SEM over test observations for one seed. Seed-to-seed variance is only reported for the Euler horizon study and for the EDM wave selection app. B.6 app. B.2.
  • Hyperparameter search was extended at boundaries, not everywhere. Direct SI for Klein-Gordon and EDM for waves were re-searched on validation. The Klein-Gordon EDM search is marked as unresolved, and the table carries a dagger tab. 2 app. B.2.
  • csFID is sensitive to layout. Spatial features penalise a reflection or rotation far more than pooled features do. The ratio for a 90 degree rotation on Euler is 7.55 for csFID versus 3.65 for cFID tab. 9 app. B.4. Spatial and pooled metrics can rank the two direct models differently. On Euler, csFID nearly ties Direct SI and EDM (difference -0.94 ± 0.90). Use the pooled metric as a diagnostic.
  • csFID details matter. The image adapter clips with a training-set quantile, uses 3 identical channels, and has no colormap. Waves and Klein-Gordon are scored on displacement only, although the forecaster also predicts a velocity channel app. B.3.
  • Velocity proxy on waves. The observed velocity is a forward difference of displacement, with zero at t=0. The paper says the supplied initial proxy gives extra information at the start. Setting it to zero at inference lowers the wave-state correlation from 0.949 to 0.871 at S=5 tab. 4 app. B.1.
  • Sign and noise conventions in the SI loss. The paper's noise scale sigma is the training parameter, and the sampler noise is sigma(1 - tau). Setting the sampler multiplier differently from the training sigma changes the sampler app. B.2.
  • Horizons differ across systems. The depth and sampler selections are per system, so tables are not comparable across systems tab. 3 tab. 6.
  • Dataset licence is not stated. The Hugging Face datasets page shows no licence tag, so redistribution of the benchmark data is not cleared by this card.
  • Algorithmic detail in appendices. Rotation-OU results depend on constants B_fit and lambda_2 from the proofs in appendix C. The main text gives only the qualitative result §3 app. C.

Lineage

  • Builds on: conditional stochastic interpolants and conditional diffusion for forecasting §1 app. A. Direct SI is taken from prior conditional SI work, and EDM from Karras et al. §4 app. B.2.
  • Related sequential forecasting: GenCast and autoregressive diffusion for turbulent flows, plus DYffusion, which uses intermediate times §1 app. A.
  • Compared against: Direct SI and EDM, both trained on endpoint pairs §4.
  • Superseded by: not known.

Source and license

Adapted from “Generative Forecasting from Coarse Observations: Does Cascading Help?” by Alexandra Spitzer, Giovanni Abati, Lorenzo Baldassari, Till Muser, Cheng Shi, Ivan Dokmanić (arXiv:2611.00686), used under CC BY 4.0. Changes: condensed and restructured for implementation, with tables, equations and algorithms taken from the paper and its code, each cited to its source. Not affiliated with or endorsed by the authors. Code citations refer to https://huggingface.co/coarse-grained-forecasting-benchmark/forecasting-models/tree/main/code at commit 1a2de037950e (MIT). Any quoted code is shown under that license.