A Deep Learning Framework for Chlorophyll Prediction in Large Marine Ecosystems: Benchmarking with a Dynamic Model and Implications for Fish Catch Forecasts

Park, Ji-Sook; Park, Jong-Yeon; Ham, Yoo-Geun; Kim, Jeong-Hwan; Jeon, Woo Jin

doi:10.5194/egusphere-2025-5673

Preprints

https://doi.org/10.5194/egusphere-2025-5673

Preprints

27 Nov 2025

| 27 Nov 2025

Status: this preprint is open for discussion and under review for Earth System Dynamics (ESD).

A Deep Learning Framework for Chlorophyll Prediction in Large Marine Ecosystems: Benchmarking with a Dynamic Model and Implications for Fish Catch Forecasts

Ji-Sook Park, Jong-Yeon Park, Yoo-Geun Ham, Jeong-Hwan Kim, and Woo Jin Jeon

Abstract. Anticipating marine ecosystem changes is critical for enabling communities to adapt to climate fluctuations and for predicting future climate by considering interactions between Earth’s physical and biogeochemical fields. Earth System Models (ESMs) simulate Earth’s multi-facet features, but their predictive capabilities remain limited due to sparse biogeochemical observations and structural uncertainties in marine biogeochemical models. Here, we develop a deep learning–based prediction system to forecast surface chlorophyll concentrations across all Large Marine Ecosystems (LMEs). Trained on multi-decadal simulations from various climate models and a coupled physical–biogeochemical reanalysis from a data assimilative ESM run, the system demonstrates skillful chlorophyll predictions comparable to ESM-based dynamic forecasts. The prediction skill arises from physical-biogeochemical coupling processes triggered by large-scale climate variability, consistent with the mechanisms previously identified in dynamical forecasts. Furthermore, predicted chlorophyll anomalies are significantly linked to interannual variability in fish catch in several LMEs, demonstrating the promise of data-driven biogeochemical forecasting to support adaptive, climate-informed marine resource management.

Received: 15 Nov 2025 – Discussion started: 27 Nov 2025

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.

Download & links

Ji-Sook Park, Jong-Yeon Park, Yoo-Geun Ham, Jeong-Hwan Kim, and Woo Jin Jeon

Status: open (until 12 Feb 2026)

Post a comment Subscribe to comment alert

RC1:
'Comment on egusphere-2025-5673', Anonymous Referee #1, 30 Jan 2026 reply
Summary

This paper develops a CNN to predict annual and monthly mean chlorophyll concentrations within Large Marine Ecosytems using surface chlorophyll and SST from the previous three months as predictors, with training primarily based on Earth System Model simulations and reanalysis. Satellite-derived chlorophyll is used for evaluation. For monthly predictions, the authors evaluate lead times from 1 to 24 months.

Overall, I found this paper interesting and potentially useful to the community. The approach of using a data-driven framework for chlorophyll prediction is timely. However, I believe that the manuscript requires substantial revision before publication. In particular, the methods section lacks sufficient detail and clarity to be fully understood and reproduced. The assessment of model skill would be strengthened by comparison to simple baselines such persistence in addition to dynamical forecasts. I would also like to see a more explicit discussion of the limitations of training a CNN on modeled data and how these limitations may affect real-world applicability. Finally, I found that the fish catch prediction section did not convincingly demonstrate utility for marine resource management.

Major comments

1) The methods section requires more detail to be understandable and reproducible. While the manuscript describes the data sources and general temporal coverage, key implementation details are ambiguous (see specific comments below). For example, explicitly stating the effective number of training and testing samples would improve transparency.

2) I think that the approach of training a CNN on model data needs stronger justification. I agree with the authors that Earth system models have large uncertainties due to parameterizations, spatial resolution, etc., which make prediction challenging. However, it is not clear how the deep learning approach mitigates these uncertainties when the training data themselves reflect ESM biases. Maybe if training on multiple models, this concern is reduced, but I would appreciate a clear statement on this. The main advantage I see to using the CNN over dynamical forecasts is the greater computational efficiency, which was only briefly mentioned. It would be helpful to include a discussion of how training the CNN on modeled data may limit the applicability to the real world.

3) The paper would benefit from discussing uncertainties related to studying chlorophyll in LMEs. Low-resolution ESMs do not resolve coastal processes well. There are also large uncertainties in satellite observations of chlorophyll in coastal waters. Additionally, there is huge spatial variability of chlorophyll within LMEs, which limits the applicability to marine resource management. These caveats and room for future work should be clearly articulated.

4) While benchmarking with a dynamic model is a good approach, I believe that this paper would be much stronger if the predictions were also benchmarked against climatological means or persistence. Given the strong autocorrelation of chlorophyll anomalies, it is difficult to assess the added value of the CNN without these comparisons.

5) I am not convinced that the forecasts presented in Section 3.5 are currently useful for marine resource management. The analysis appears exploratory, with species, LMEs, lag times, and significance thresholds selected in a way that risks cherry-picking statistically significant relationships. Given the large number of combinations explored, it is expected that some relationships will appear significant at the 90% confidence level by chance alone. A more systematic approach is needed. Possible alternatives include focusing on total catch (if available), providing a clear justification for the LMEs and species examined, or targeting regions where fisheries collapses have plausibly been linked to environmental variability. Finally, the authors must acknowledge a major caveat of the fish catch dataset: reported catch depends strongly on fishing effort, management, and reporting practices, not solely on environmental conditions.

Minor comments

Abstract

Consider specifying the prediction timescales and lead times in the abstract.

Introduction

I think that the need for prediction using deep learning could be more strongly motivated in the introduction.

It would be very helpful to clarify lead times and averaging windows in the introduction. What scales are relevant for ecosystem management?

Line 37:  I’m not sure if it’s fair to say that the performance for biogeochemical variables remains limited. There are papers showing skillful predictions of NPP, DIC, and other biogeochemical variables. Please see citations below:

Mogen, S. C., Lovenduski, N. S., Yeager,S., Keppler, L., Sharp, J., Bograd, S.J., et al. (2023). Skillful multi-monthpredictions of ecosystem stressors in thesurface and subsurface ocean. Earth'sFuture, 11, e2023EF003605. https://doi.org/10.1029/2023EF003605

Ilyina, T., Li, H., Spring, A., Müller, W. A., Bopp, L., Chikamoto, M. O., et al. (2021). Predictable variations of the carbon sinks and atmospheric CO2 growth in a multi-model framework. Geophysical Research Letters, 48, e2020GL090695. https://doi.org/10.1029/2020GL090695

Krumhardt, K. M., Lovenduski, N. S., Long, M. C., Luo, J. Y., Lindsay, K., Yeager, S., & Harrison, C. (2020). Potential predictability of net primary production in the ocean. Global Biogeochemical Cycles, 34, e2020GB006531. https://doi.org/10.1029/2020GB006531

Brady, R.X., Lovenduski, N.S., Yeager, S.G. et al. Skillful multiyear predictions of ocean acidification in the California Current System. Nat Commun 11, 2166 (2020). https://doi.org/10.1038/s41467-020-15722-x

Methods

Line 96: Why not use a gap-filled data product or one that merges more instruments, like OC-CCI or GlobColour? Can you please also clarify how MODIS/SeaWIFS data were accessed and processed?

Line 103: I am confused by the zero-filling strategy applied here. While this seams reasonable for polar night regions, where chlorophyll concentration is nearly zero, how can you justify filling in grid cells obscured by clouds with zero? Please clarify this section.

It may be worth mentioning that the satellite-derived chlorophyll data is biased by selective sampling in clear sky conditions, while the ESM-based training data is not. This may further complicate the applicability of the ESM-trained CNN to real-world predictions.

Line 112: Please clarify the gap-filling treatment applied to simulated chlorophyll. Are observational data gaps being imposed on the model output? If so, how is physical consistency ensured?

Figure 1. Typo in SeaWIFTS

Results

Line 154: Did you experiment with different input time windows? Why 3 consecutive months?

Line 156: Why were 16 LMEs selected?

It would be extremely helpful to include a labeled map of all LMEs. Perhaps in supplemental information?

Line 173: I would consider revising this sentence. While the inclusion of surface chlorophyll as a predictor improves forecast skill, this may largely reflect the persistence and autocorrelation of chlorophyll anomalies rather than the capture of nonlinear ecological signals.

Line 194: I find the term “initialized” confusing here, as it implies a dynamical forecasting system. Additionally, were different months tested? I wonder if northern and southern hemispheres would benefit from different input months.

Line 195: Can you more clearly state here that the forecasts were initialized using real-world observations of SST and chlorophyll for the previous 3 months?

Figure 3: I suggest revising this figure. I found it hard to see the stars and a bit blurry when I tried to zoom in.

I would appreciate some clarification on the lead time and time averaging. In the caption, the authors say that the forecast lead time is 1 year. To me, this implies predicting values one year out, not the annual mean values of the upcoming year. It’s also not clear which months these annual means include. Do they include the month of January for that year, which is also used as input data?

Line 214: Similar to my previous comment: I’m not sure that it’s fair to say this unless you were using a different biogeochemical variable as input to predict chlorophyll. This is why benchmarking with a persistence forecast would be valuable.

Line 217: A map of LME 11 and LME 30 would be helpful.

Line 217: It would be helpful for the authors to explicitly state how ensemble members are generated in the CNN framework, as the term “ensemble” may otherwise be interpreted in a dynamical modeling sense. “Extending the forecast up to 24 months” also makes it sound like the CNN in stepping forward in time, when I assume that separate models are trained for each lead time. I would appreciate a clearer explanation of what information the CNN is using at these longer horizons.

Figure 4: It is interesting that the SHAP values are high in locations that are far away from the LMEs. Has the model learned a teleconnection? I think more discussion on this is needed.

Line 228: I would consider deferring the discussion of ENSO until the section below.

Figure 6: Please address concerns about cherry-picking. Does a chlorophyll lag time of 0 mean that the annual mean of chlorophyll was used to predict fish catch of that same year? Is that useful for real world applications?

Reply
Citation: https://doi.org/10.5194/egusphere-2025-5673-RC1
RC2:
'Comment on egusphere-2025-5673', Anonymous Referee #2, 04 Feb 2026 reply
This work presents a deep Learning framework to predict surface chlorophyll concentrations and anomalies across large marine ecosystems, with implications for fish catch forecasts.
The abstract and the introduction well describe the core idea and its fundamentals: the interactions between Earth’s physical and biogeochemical fields is important for predicting future climate and the marine biogeochemical variability is critical to advance climate predictions based on bio-climate interactions.
Nonetheless, the methods and results section can be deeply improved in order to clarify the purposes of the research, its development and its scientific novelty.

The Method Section offers a detailed overview of the deep learning architecture, together with datasets information, sensitivity analysis and prediction performances information. Despite that, the description of the architecture lacks some important details, and the dataset description, though comprehensive, is presented in a confusionary way, without properly describing the variables collected and their role in training-validation-test phases, a fact that reduces readability and reproducibility.
The architecture developed for this project is a Convolutional Neural Network. Despite the authors having dedicated a paragraph of Methods Section and a paragraph of Results section to the description of the architecture, several fundamental aspects remain unclear—particularly the dimensions of the input and output data—reducing the clarity of the project’s objectives and implementation.
The research question behind this project and consequently research purposes (i.e. the relevance of modeling mean chlorophyll within LMEs and the rationale behind using entire 2D maps to derive a single pointwise mean value for each LME) appears confusionary, a lack of clarity that is also reflected in the results. It is not particularly clear the task the manuscript intends to solve, and in particular the objective of some experiments (i.e. mechanisms underlying chlorophyll prediction skills, described in Figure 4, and the capacity to model interannual fish catch variations with chlorophyll anomalies as environmental drivers) and which is the scientific novelty they bring.
Moreover, the description of the experiments and of the results appears not always clear, and more explanations (i.e. a more detailed description of the content of Figure 4, and of the relationship between the anomaly correlation skill behavior described in figs 4a and 4c with the maps of figs 4b and 4d) would improve readability and strengthen the paper as they would support the research question posed by the authors. Finally, the descriptions of certain figures, such as Figures 4 and 5, lack sufficient detail, limiting the comprehension of both the analyses conducted and the importance and relevance of the results obtained.

In consideration of the previous points, the paper is acceptable for publication after major revisions.
A list of punctual issues is listed below.

ABSTRACT:
(L13-14): Enhance clarity and focus on this sentence to be more consistent with the problem presented.

(L20): The sentence emphasizes the relevance of physical–biogeochemical coupling processes; however, it remains unclear whether the network explicitly learns this coupling or merely reproduces its effects, as well as the mechanisms by which such learning or reproduction is achieved.

(L22): The term “chlorophyll anomalies” is introduced, but it is not defined, together with the baseline used for its computation. The entire article strengthens on this aspect, but there is no formal definition of anomaly.

INTRODUCTION:

(L35): The inclusion of references to the definition of ESMs would facilitate a deeper understanding of the purposes of the project.

(L50): Deep learning models are highly sensible on data coverage. In particular, observational gasps and data-sparse components represent a huge limitation for the majority of deep learning approaches. Even if their usage grows with the increasing availability of data, sparse coverage still represents a limit for these models. A clearer explanation of the statement asserting that deep learning methods are well suited to data-sparse components would strengthen the justification for adopting a deep learning approach for this application.

(L62): The manuscript does not clearly describe the outputs of the deep learning model. Both chlorophyll concentrations and chlorophyll anomalies are presented as model products; however, the definition and interpretation of the anomaly are not provided. Clarification of this aspect would improve the reader’s understanding of the overall study. Furthermore, it is unclear whether each LME is modeled independently or whether the model produces a global output from which individual LMEs are subsequently extracted and analyzed.

(L65-68): I think a re-organization of the last sentences of the introduction would enhance the comprehension of the project. The current description of the dataset appears overly detailed for an introductory section, while some key elements, such as a clear definition of the model outputs, are not sufficiently addressed. It is therefore recommended to revise these passages by emphasizing the general characteristics of the proposed algorithms and providing only high-level information about the dataset, while relocating the detailed dataset description to the dedicated method section.

METHODS:

Section 2.1: the architectural description lacks key details required for reproducibility, such as a comprehensive table of all hyperparameters and a clear rationale for the choice of the proposed architecture and its components, such as including the use of GELU activations and the selected loss function. To further improve the clarity of the manuscript, it is recommended to present the network architecture, dataset, and validation strategy in separate subsections.

(L91): the concept of anomaly correlation coefficient is introduced, but not defined. Including its definition, along with a brief description, would enhance the reader’s understanding of the results.

Section 2.2 describes the dataset used, including the input, validation, and test sets, and provides details on input data preprocessing. I recommend reorganizing this section to clarify the distinctions between datasets used for different purposes. Additionally, more detail on the input data preprocessing would improve clarity, as the structure of the input data is not fully specified. Specify source, variables, spatial resolution, temporal frequency of data used; in particular, clarify which dataset collects the input variables used for training, validation and test. Use a table if it can help. Moreover, it is unclear whether the inputs consist of concatenated global 2D maps of SST and chlorophyll anomalies or of 2D maps defined separately for each LME. Likewise, the description of the network output lacks clarity: it is not evident whether the output represents a mean chlorophyll value across all LMEs or a spatial map over each LME, nor whether the model predicts chlorophyll concentrations, chlorophyll anomalies, or both.

(L103): The input mask fills missing values with zeros. It would be helpful if the authors could provide additional insight into the rationale behind this choice. In particular, further clarification on whether missing values and land points are treated differently, and on the network’s ability to distinguish between these cases, would enhance the reader’s understanding.

(L124): Paragraph 2.3 introduces SHAP as a method for interpreting model predictions and identifying dominant spatial drivers (L118). However, the role of SHAP in this context is not entirely clear. Given that the network inputs consist of SST and chlorophyll anomalies, one would expect the analysis to highlight the relative importance of these input variables. Instead, at (L124) it is stated that feature (i) corresponds to a specific grid point in the input map, which introduces some ambiguity regarding what information the SHAP analysis is intended to convey. A clearer explanation of how features are defined and how SHAP results should be interpreted would improve the clarity and understanding of the results.

Section 2.4: the scope of this section appears scientifically obscure. Chlorophyll (or its anomaly) timeseries from satellites or from ESM models can be directly used to predict catch timeseries. Which are the added values of using NN derived chlorophyll? One would expect, at least, a comparison between catch timeseries predicted using chlorophyll from satellites, or to see the advantage of using the NN derived chlorophyll.

RESULTS:
Section (3.1) presents a very interesting and informative analysis; however, some of the architectural details discussed here would be more appropriately included in the Methods section, within the description of the model architecture. In addition, to improve the comprehensibility of the architecture described in the Methods section and to maintain focus on the model’s results, it is suggested to move this sensitivity analysis to a Supplementary Materials section.

(L150): In the caption of Figure 2, the baseline model is described as sharing the architecture of the reference model, while differing in certain training settings, such as the loss function. This suggests that the reference model represents an optimized version of the baseline. However, at line 148 it is stated that the sensitivity analysis presented in this paragraph originates from the reference model, with a single component modified in each experiment. Could the authors clarify the contributions of these sensitivity experiments to the reference model, and how the reference model was optimized relative to the baseline? Providing this explanation would help improve the reader’s understanding of the experimental design and the relationship between the baseline, reference, and sensitivity models.

(L155): The concept of prediction skill is not defined, and its meaning remains somewhat unclear. In particular, in Figure 2, it is not evident what exactly the prediction skill measures. Including a brief description would enhance both clarity and will facilitate the comprehension of the proposed results.

(L175): Could the authors clarify the statement, “The inclusion of additional input datasets generally improved the model’s prediction skill”? It should be noted that adding input variables does not necessarily guarantee improved model performance; if the additional inputs have weak correlation with the target, their inclusion could potentially lead to overfitting. Providing a reference and a more detailed explanation would help clarify this point and strengthen the interpretation of the results. Moreover, the choice to include chlorophyll as input variable when predicting chlorophyll itself should be clarified. Moreover, it would be helpful to provide a table which contains for each test the input variables used for it. It is somehow difficult to reconnect the text to names listed in figure 2.

From Figure 3a, it appears that the CNN output is represented as a single mean value for the entire LME, resulting in a uniform color. Could the authors clarify whether this interpretation is correct, or if the correlation is instead computed at the level of individual grid points? Providing this clarification would help improve the reader’s understanding of the figure and the network’s output. Based on Figure 1, the inputs appear to consist of timeseries of two-dimensional spatial fields, whereas the outputs correspond to timeseries of zero-dimensional quantities (i.e., single surface values). If this interpretation is correct, the rationale for adopting a two-dimensional–to–zero-dimensional mapping should be explicitly discussed. In particular, it would be helpful to clarify the intended purpose and advantages of this approach compared to the use of a simple spatial average, as well as to articulate the scientific novelty that this methodology is expected to provide.

Improve the quality and clarity of the figure 3: y axis is missing the label and unit, and the text should be enlarged.

(L195): The exact number of CNN input variables is not entirely clear. While SST and chlorophyll anomalies are listed as inputs in the introduction (L62), a different description appears later, stating that the model was “tested with a combination of physical and biogeochemical inputs, that is, SST only, chlorophyll only, and both SST and chlorophyll.” Could the authors kindly clarify the reason for this apparent discrepancy? If a sensitivity analysis was conducted to determine the optimal set of input variables, it would be helpful to briefly describe the procedure. Otherwise, specifying the exact input variables used in the current model would improve clarity for the reader.

(L213): The manuscript states that “including surface chlorophyll anomalies, either alone or as an additional predictor, substantially increased the number of LMEs where the model achieved high prediction skill.” In the introduction, chlorophyll anomalies are already presented as an input to the model, whereas here it appears that they are added subsequently. Could the authors kindly provide a more detailed explanation of how the input data are structured and used? Clarifying this point would improve the reader’s understanding of the model setup and the role of different predictors.

(L215-220): The caption of Figure 4 lacks clarity, and the prediction task described in lines 215–218 would benefit from a more detailed explanation. In particular, the inputs and outputs of the task should be explicitly specified, and the procedure used to compare predictions with observations should be described more clearly. For example, it is unclear which quantities are being compared at each grid point in Figures 4a and 4c. Additionally, the captions for Figures 4b and 4d are ambiguous; as currently presented, it appears that two sequences of three maps are shown. Consideration could be given to splitting this content into two separate figures in order to improve readability and facilitate the reader’s understanding of the task.

The analysis presented in the latter part of paragraph 3.2 is interesting, and the results shown in Figure 4 are valuable. Nevertheless, the paragraph would benefit from a more detailed explanation of what is the content and the relevance of figures 4a and 4c, together with the implications between Figures 4a and 4b, as well as between Figures 4c and 4d. Clarifying these connections would greatly enhance the reader’s understanding of the results and their interpretation.

(L239): The manuscript states that “the recurrence of this pattern in the model’s predictions indicates that it captures subsurface ocean memory in addition to surface signals.” Could the authors clarify why the recurrence of this pattern is interpreted as evidence of subsurface ocean memory, given that subsurface variables do not appear to have been used or introduced as input to the model? Providing additional explanation would help improve the reader’s understanding of this conclusion.

(L248): For the sake of comparison, it would be helpful to include the ENSO dynamics in a Supplementary Material section, providing a baseline for reference alongside Figures 4b and 4d.

L265-270: move in material and method the description of models.

Explain better how correlation between satellite chlorophyll and predictions by DL and dynamics are computed.

In figure 5, use labels (DL and dynamics) that are consistent throughout the paper and are clear; if figure 5a and 5b provide the same information, consider simplification and use only one, otherwise, clarify the distinction.

In Fig. 5a, the numbers of significant correlations are 15 for DL and 16 for dynamics. It appears to me to have quite poor performance results. Please reformulate L281-282.

(L284): Some regions are listed as examples of comparable performance habits, but the Fig 5a does not show explicitly these regions. Indicating at which bars of the plot they correspond would increase the clearness of the results. Moreover, a map with the 66 LME is missing in the paper.

To evaluate the validity of using NN chlorophyll predictions instead of observed chlorophyll data for fish catch prediction, it would be informative to include a comparison, for example with results obtained from a linear regression model using satellite chlorophyll observations. Alternatively, please clarify the reason for this methodological choice.

Figure 6 shows only 2 LME. Providing additional information about the correlation between chlorophyll and fish catch in the other LMEs could strengthen the results.

Improve the quality and clarity of the figure 6: y axis is missing the label and unit and the text needs to be enlarged. Does y-axis represent the correlation coefficient between fish catch and chlorophyll anomalies, or the comparison between predicted and observed fish catch?

DISCUSSION & CONCLUSION:
The conclusion and discussion section clearly summarizes strengths and limitations of the approach and the value of the sensitivity analysis. However, a few aspects could be better presented.

(L340): The phrase “while capturing physically interpretable signals underlying chlorophyll variability” could benefit from clarification. Since the CNN inputs are SST and chlorophyll anomalies, it would be helpful to specify whether this comment refers specifically to SST or to other physical signals. Providing this clarification would improve the reader’s understanding of the model’s interpretation.

(L340): The statement that “the model successfully reproduces the known ocean–climate process” could benefit from further elaboration. Providing a brief explanation of which specific ocean–climate processes this sentence refers to would help strengthen the interpretation of the results and improve clarity for the reader.

(L362): The statement that “sensitivity tests show that surface chlorophyll anomalies captured subsurface variability” would benefit from further clarification. From the manuscript, it appears that the sensitivity analysis was primarily performed to optimize the network architecture and input data. It is therefore not immediately clear how this analysis supports the conclusion regarding subsurface variability. Providing a more detailed explanation of the connection, or the underlying correlations, would help the reader better understand the interpretation of the proposed results.

Reply
Citation: https://doi.org/10.5194/egusphere-2025-5673-RC2

Ji-Sook Park, Jong-Yeon Park, Yoo-Geun Ham, Jeong-Hwan Kim, and Woo Jin Jeon

Viewed

Total article views: 393 (including HTML, PDF, and XML)

HTML	PDF	XML	Total	BibTeX	EndNote
197	179	17	393	15	13

HTML: 197
PDF: 179
XML: 17
Total: 393
BibTeX: 15
EndNote: 13

Views and downloads (calculated since 27 Nov 2025)

Month	HTML	PDF	XML	Total
Nov 2025	40	9	3	52
Dec 2025	49	73	7	129
Jan 2026	84	79	3	166
Feb 2026	24	18	4	46

Cumulative views and downloads (calculated since 27 Nov 2025)

Month	HTML	PDF	XML	Total
Nov 2025	40	9	3	52
Dec 2025	49	73	7	129
Jan 2026	84	79	3	166
Feb 2026	24	18	4	46

Viewed (geographical distribution)

Total article views: 375 (including HTML, PDF, and XML) Thereof 375 with geography defined and 0 with unknown origin.

Country	#	Views	%

Latest update: 08 Feb 2026

Short summary

We developed a deep learning system to predict future ocean phytoplankton, the base of the marine food web. Using long-term records from climate model simulations and past ocean data, it provides skillful chlorophyll forecasts across global coastal regions, comparable to those from dynamic climate model forecasts. The predicted chlorophyll also explains historical changes in fish catch, offering a new tool to help communities prepare for climate-driven marine ecosystem changes.


Total:	0
HTML:	0
PDF:	0
XML:	0