- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes GEWorld, a stateful genotype-by-environment (G E) modeling framework in which genotype state and time-varying environmental factors drive state transitions, while sparse phenotypic observations are assimilated to update latent states conditioned on genotype and environment. The framework supports static phenotype prediction and dynamic trajectory forecasting. Experiments across multiple crops, including factual and counterfactual forecasting settings, demonstrate the effectiveness of GEWorld. Further analyses provide insight into how genotype and environment influence phenotypic trajectories.
Critical strengths
- The paper addresses an important challenge in genotype-to-phenotype prediction by modeling dynamic G×E interactions and enabling state updates under changing environmental conditions.
- The paper evaluates both static and dynamic phenotype prediction across multiple crops and further investigates counterfactual forecasting using crop simulations, demonstrating the effectiveness of GEWorld and providing understanding about how genotype and environmental factors interact to influence crop phenotypes.
Critical weaknesses
-
Insufficient justification and ablation analysis of the stateful modeling framework. The architectural novelty of GEWorld lies mainly in the “Gated G E Initialization” and “Observation Assimilation and State Transition” modules. However, it remains unclear why a Mamba-based state-space model is preferred over conventional temporal models, such as RNNs or Transformers in general world models.
-
The paper does not clearly specify which mentioned datasets are utilized for train/val/test split. In addition, the counterfactual evaluation relies on APSIM simulations, and Table S8 reports substantially higher sign agreement for counterfactual forecasting than for factual forecasting. Without a clear description of the data splits and evaluation protocol, it is difficult to assess whether these results reflect generalizable environmental responses or overfitting to the training data.
Questions for authors
- Why was Mamba selected for the state transition model? How does it compare with conventional temporal models under comparable settings?
- Why is sign agreement substantially higher in APSIM-based counterfactual forecasting than in factual forecasting (Table S8)? Could the authors clarify the evaluation protocols and further assess whether the model accurately captures intervention-induced changes in phenotype?
- How should the embedding visualization in Figure S4 be interpreted? Maize shows less distinct clustering by phenotype than rice, despite achieving better phenotype prediction performance. Could the authors explain this discrepancy?
4 comments
Rebuttal Part 2/2
Q2. Why is sign agreement higher for counterfactual forecasting in Table S8, and does the model capture intervention-induced changes?
Table S8's factual and counterfactual rows use different panels and contrasts, so their scores are not directly comparable. Direction agreement can also reflect the average environmental response. We will clarify this interpretation. We therefore added a controlled APSIM weather experiment. For wheat and sorghum, paired runs share identical simulator settings and the first 84 days, verified by deterministic replay. From day 85, only future weather changes: rainfall is halved or maximum/minimum temperatures increase by 10°C. The benchmark contains 3,000 trajectories and 2,000 intervention pairs, split by weather year into 70/15/15 training/validation/test years, keeping all branches and initial-water conditions of each year together. Each model assimilates the common history once, copies its state, and predicts both branches using future weather only. We compare the predicted intervention-minus-factual change with the APSIM change.
We evaluate intervention effects using MAE across both interventions and all 12 forecast weeks. For GEWorld, we average predictions from three initializations before computing MAE. Lower values indicate more accurate effect estimates.
| Crop / trait | GEWorld | Zero effect | Training mean effect | Ridge |
|---|---|---|---|---|
| Wheat biomass | 20.907 | 86.501 | 51.181 | 49.099 |
| Wheat grain | 7.663 | 24.106 | 13.859 | 13.881 |
| Wheat LAI | 0.162 | 0.377 | 0.325 | 0.307 |
| Sorghum biomass | 71.302 | 131.723 | 127.131 | 120.060 |
| Sorghum grain | 35.820 | 71.496 | 56.520 | 53.680 |
| Sorghum LAI | 0.253 | 0.354 | 0.332 | 0.325 |
GEWorld has lower effect MAE than all three baselines in all six pooled comparisons. This supports prediction of intervention magnitudes in this controlled simulation benchmark. Improvement over the zero-effect baseline indicates that the predicted responses capture meaningful intervention signals. The gains over the training-mean and ridge baselines further suggest that GEWorld captures variation in response magnitudes beyond an average effect or a linear approximation.
We have summarized these results in Section 4.2 (RQ3), and provided the full evaluation in Appendix C.6 of our revision.
Q3. How should Figure S4 be interpreted when maize clusters less but predicts better?
Maize can be predicted accurately without forming distinct clusters because the task is continuous trait regression. Predictions can follow a smooth trait gradient through the representation: nearby genotypes can have gradually changing phenotypes, with no visible boundary between groups. Conversely, visibly separated rice clusters need not separate samples along the directions most relevant to the target trait. Figure S4 further compresses the initialized state into two UMAP dimensions; UMAP emphasizes neighborhood structure, without optimizing preservation of phenotype-predictive information.
The maize panel also has a strong predictable environmental component. A training-only environment-mean baseline already reaches in maize, compared with in rice. Thus, much of maize's overall predictability is accessible from known environmental groups without requiring visually distinct genotype clusters. This provides a concrete explanation for why maize can predict better despite weaker clustering; it does not imply that maize has stronger genetic separation.
We report test as mean ± sample SD across five genotype splits. Scaling and PCA are fitted on training data, and ridge regularization is selected on validation data.
| Predictor | Maize | Rice |
|---|---|---|
| Stored single-model decoder | 0.6404 ± 0.0047 | 0.4699 ± 0.0657 |
| Full-state ridge | 0.6344 ± 0.0106 | 0.4854 ± 0.1711 |
| 2D PCA ridge | 0.5617 ± 0.0054 | 0.4140 ± 0.1030 |
| Training-only environment mean | 0.5746 ± 0.0182 | 0.0169 ± 0.0121 |
The full-state ridge also outperforms the 2D PCA probe in maize by 0.073 R², supporting predictive information beyond a two-dimensional linear projection. We will clarify in Figure S4's caption that cluster visibility illustrates representation geometry and should not be used to rank predictive accuracy across crops.
We have clarified this interpretation in Section 4.2 (RQ4), and added the predictive probes in Appendix C.4 of our revision.
Thanks for the authors' response. Most of my concerns have been addressed. I'd like to maintain my original socre for a weak acceptance.
We sincerely thank the reviewer for their valuable feedback and for the time and effort devoted to carefully evaluating our responses. The insightful comments have helped us further improve the clarity and presentation of our manuscript. We also greatly appreciate the reviewer’s positive assessment and continued support of our work.
Rebuttal Part 1/2
We thank the reviewer for the careful reading and constructive questions. We will address each of them in turn.
W1. Insufficient justification of the stateful framework
The Model esign is biologically motivated. Within-season phenotype is better viewed as a partially observed physiological process: genotype sets response capacity, weather drives development over time, and field traits are sparse, noisy readouts of that latent state. A stateful assimilate–rollout loop matches this structure: initialize from G×E, correct when measurements arrive, then open-loop under future environments, unlike a static G×E map.
We therefore use a Mamba-inspired selective SSM as the transition: its input-dependent gating lets current weather and time control what developmental memory is retained, aligning with stage- and stress-dependent crop dynamics. Whether this Mamba-style transition outperforms GRU/RNN/Transformer is answered empirically in Q1.
W2. Unclear splits and concern that Table S8 overstates environmental responses
We fully agree with the reviewer’s concerns. In our setting, train/val/test are genotype-grouped: held-out genotypes in known environments, not unseen sites. More importantly, Table S8’s “factual” and “counterfactual” rows are not matched scores on the same samples,they mix panels and contrasts, so direction agreement alone can look strong. We therefore clarify the split protocol, reinterpret Table S8 as cross-environment consistency, with an environment-mean baseline and magnitude errors, and add a fixed-history APSIM weather benchmark that changes only post-cutoff weather; protocols and numbers are in Q2.
Q1. Why was Mamba selected, and how does it compare under comparable settings?
A selective SSM lets environmental/time inputs modulate state evolution via input-dependent decay, update, and readout, while keeping a recurrent interface for assimilation. The module is a Mamba-inspired, one-step selective SSM, with internal memory rebuilt from the shared latent state each step.
We compare the selective SSM, GRU, RNN, and causal Transformer on sorghum TERRA-REF using a 70% observed prefix. All four models use a latent width of D=128 and share the encoders, genotype FiLM, assimilation GRU, decoder, optimizer, and early-stopping settings. Each model is evaluated with the seasonal curve enabled and disabled. We use five independent genotype-disjoint splits, each with a 70/15/15 train/validation/test ratio. The main-text experiments vary random seeds under a fixed genotype holdout, whereas these controls assess whether the models’ relative performance remains robust across different held-out genotype sets.
The selective SSM achieves the highest mean test R2 in all four settings. Its cover gains over GRU, RNN, and Transformer are 0.0536, 0.0453, and 0.0999 with the seasonal curve enabled, and 0.1137, 0.0790, and 0.1665 with it disabled. Its advantage with the curve enabled also suggests that the learned dynamics complement the seasonal prior.
We have summarized the transition comparison in Section 4.2 (RQ4), and provided the details in Appendix C.3 of our revision.