the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
| 16 Oct 2024
PaleoSTeHM v1.0-rc: a modern, scalable spatio-temporal hierarchical modeling framework for paleo-environmental data
Abstract. Geological records of past environmental change provide crucial information for assessing long-term climate variability, non-stationarity, and nonlinearities. However, reconstructing spatio-temporal fields from these records is statistically challenging due to their sparse, indirect, and noisy nature. Here, we present PaleoSTeHM, a scalable and modern framework for spatio-temporal hierarchical modeling of paleo-environmental data. This framework enables the implementation of flexible statistical models that rigorously quantify spatial and temporal variability from geological data with clear distinguishing between measurement and inferential uncertainty from process variability. We illustrate its application by reconstructing temporal and spatio-temporal paleo sea-level changes across multiple locations. Using various modeling and analysis choices, PaleoSTeHM demonstrates the impact of different methods on inference results and computational efficiency. Our results highlight the critical role of model selection in addressing specific paleo-environmental questions, showcasing the PaleoSTeHM framework's potential to enhance the robustness and transparency of paleo-environmental reconstructions.
-
Notice on discussion status
The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.
-
Preprint
(7707 KB)
-
The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.
- Preprint
(7707 KB) - Metadata XML
- BibTeX
- EndNote
- Final revised paper
Journal article(s) based on this preprint
Interactive discussion
Status: closed
-
RC1: 'Comment on egusphere-2024-2183', Anonymous Referee #1, 25 Nov 2024
The authors present a novel spatio-temporal hierarchical modeling framework designed for examining paleo-environmental data. It provides an in-depth discussion of the underlying architecture of the PaleoSTeHM software and showcases its capabilities through several case studies focused on paleo sea-level data. This paper showcases the PaleoSTeHM software, which represents a significant and valuable contribution to the field. The integration of machine learning techniques with a variety of Bayesian inference methods marks a notable advancement. However, the paper's structure, terminology and layout would benefit from further refinement. It assumes considerable prior knowledge, which may pose challenges for readers. I have outlined several questions and observations regarding the explanations, along with substantial content related feedback in the attached PDF. Despite these hurdles, the framework's innovative approach and potential for broad applicability highlight its promise as a transformative tool in paleo-environmental research.
-
AC2: 'Reply on RC1', Yucheng Lin, 26 Jan 2025
We thank the reviewer for recognizing the importance and thoroughness of this study, as well as for acknowledging the effort invested in developing the PaleoSTeHM framework. We also greatly appreciate the reviewer’s detailed comments and constructive feedback that significantly improve the quality of this paper. We have addressed all comments in the attached pdf file in blue.Â
-
AC2: 'Reply on RC1', Yucheng Lin, 26 Jan 2025
-
CC1: 'Comment on egusphere-2024-2183', Andrew C Parnell, 20 Dec 2024
I very much enjoyed reading the paper by Lin et al. This is an extremely impressive and thorough piece of work. The associated Python framework is extremely well done, and I was very impressed to see so many options given for how the models are fitted and plotted. My only real concern about this work is the functionality for those who are not experts in Python (or Pyro) as the vast majority of users would be. There are very thorough notebooks in the tutorial section of the Github repo but these are not really helpful for those who want to do a quick straightforward model. My guess is that most users want to fit a GP model using the default values for time uncertainty, error variance, kernel choice, etc, and would like a simple guide for how to get their data from the Excel spreadsheet through the PalaeoSTEHM pipeline. Going even further I would strongly encourage the authors to create a proper Python package to simplify the instructions and coding.Â
One notable thing I couldn’t see in the notebooks I ran (or in the paper) was convergence checking for the model. I would say this is absolutely vital for having any faith in the results. Models of this complexity can be extremely difficult to obtain convergence on, and there is a whole range of summary stats available for this in Pyro. It should be part of the default workflow everywhere. Perhaps it is for some scripts and I’ve missed it, but it certainly isn’t discussed in the paper. On a similar vein I’d like to know if the model is calibrated, via scoring rules or even just some posterior predictive distributions (though these can be tricky with bivariate uncertainties), and some kind of out-of-sample performance metrics as would be common in standard ML pipelines.Â
Otherwise I really enjoyed the paper and I’m super excited to see how this develops. There were a number of poor sentences which I’ve highlighted below but I don’t think I’ve got all of them. It just needs another language check.Â
L32: Change-points
L35: I’d put the reference to the GitHub repo here so people can start coding without needing to read the whole paper.Â
Table 1: I’d just review some of these definitions. The conditional probability one about conditioning on an unknown quantity doesn’t read quite right. I also think you: should include one for parameter itself; adjust the line spacing or add horizontal lines to separate the entries better; re-write the likelihood one; and change the uncertainty one which seems to be a frequentist definition.Â
Fig 1: External
Fig 1 caption: Platforms
L174: I assume the number of change points is fixed and not learnt?
L176: delete ‘and’
L187: Mu(t) or mu(X) (as used in Eq 10)?
L201: will be shown in Section 2
Table 2: I got confused by what the sampling covariance is and how it is calculated for deterministic models. Please expand in the text
Eq 15 (and perhaps others). The usual way to present normal distributions is mean and variance, not sd.Â
Fig 5 (bottom right) and others. It always bugs me slightly that the uncertainty in the rate for the present is more unknown when it is the period when we have the most data. Is there a way to solve this with these models? It strikes me that we should be using temporally non-stationary models that allow for far reduced variance (and hence variance on the derivative) to capture the rate of the most recent periods.ÂCitation: https://doi.org/10.5194/egusphere-2024-2183-CC1 - AC3: 'Reply on CC1', Yucheng Lin, 26 Jan 2025
-
RC2: 'Comment on egusphere-2024-2183', Kerry Gallagher, 25 Dec 2024
-
AC1: 'Reply on RC2', Yucheng Lin, 26 Jan 2025
We thank the reviewer for this thoughtful and encouraging feedback. We appreciate the recognition of the study's importance and the effort behind the development of the PaleoSTeHM framework. We have addressed all comments and suggestions in the attached pdf file in blue text.
-
AC1: 'Reply on RC2', Yucheng Lin, 26 Jan 2025
Interactive discussion
Status: closed
-
RC1: 'Comment on egusphere-2024-2183', Anonymous Referee #1, 25 Nov 2024
The authors present a novel spatio-temporal hierarchical modeling framework designed for examining paleo-environmental data. It provides an in-depth discussion of the underlying architecture of the PaleoSTeHM software and showcases its capabilities through several case studies focused on paleo sea-level data. This paper showcases the PaleoSTeHM software, which represents a significant and valuable contribution to the field. The integration of machine learning techniques with a variety of Bayesian inference methods marks a notable advancement. However, the paper's structure, terminology and layout would benefit from further refinement. It assumes considerable prior knowledge, which may pose challenges for readers. I have outlined several questions and observations regarding the explanations, along with substantial content related feedback in the attached PDF. Despite these hurdles, the framework's innovative approach and potential for broad applicability highlight its promise as a transformative tool in paleo-environmental research.
-
AC2: 'Reply on RC1', Yucheng Lin, 26 Jan 2025
We thank the reviewer for recognizing the importance and thoroughness of this study, as well as for acknowledging the effort invested in developing the PaleoSTeHM framework. We also greatly appreciate the reviewer’s detailed comments and constructive feedback that significantly improve the quality of this paper. We have addressed all comments in the attached pdf file in blue.Â
-
AC2: 'Reply on RC1', Yucheng Lin, 26 Jan 2025
-
CC1: 'Comment on egusphere-2024-2183', Andrew C Parnell, 20 Dec 2024
I very much enjoyed reading the paper by Lin et al. This is an extremely impressive and thorough piece of work. The associated Python framework is extremely well done, and I was very impressed to see so many options given for how the models are fitted and plotted. My only real concern about this work is the functionality for those who are not experts in Python (or Pyro) as the vast majority of users would be. There are very thorough notebooks in the tutorial section of the Github repo but these are not really helpful for those who want to do a quick straightforward model. My guess is that most users want to fit a GP model using the default values for time uncertainty, error variance, kernel choice, etc, and would like a simple guide for how to get their data from the Excel spreadsheet through the PalaeoSTEHM pipeline. Going even further I would strongly encourage the authors to create a proper Python package to simplify the instructions and coding.Â
One notable thing I couldn’t see in the notebooks I ran (or in the paper) was convergence checking for the model. I would say this is absolutely vital for having any faith in the results. Models of this complexity can be extremely difficult to obtain convergence on, and there is a whole range of summary stats available for this in Pyro. It should be part of the default workflow everywhere. Perhaps it is for some scripts and I’ve missed it, but it certainly isn’t discussed in the paper. On a similar vein I’d like to know if the model is calibrated, via scoring rules or even just some posterior predictive distributions (though these can be tricky with bivariate uncertainties), and some kind of out-of-sample performance metrics as would be common in standard ML pipelines.Â
Otherwise I really enjoyed the paper and I’m super excited to see how this develops. There were a number of poor sentences which I’ve highlighted below but I don’t think I’ve got all of them. It just needs another language check.Â
L32: Change-points
L35: I’d put the reference to the GitHub repo here so people can start coding without needing to read the whole paper.Â
Table 1: I’d just review some of these definitions. The conditional probability one about conditioning on an unknown quantity doesn’t read quite right. I also think you: should include one for parameter itself; adjust the line spacing or add horizontal lines to separate the entries better; re-write the likelihood one; and change the uncertainty one which seems to be a frequentist definition.Â
Fig 1: External
Fig 1 caption: Platforms
L174: I assume the number of change points is fixed and not learnt?
L176: delete ‘and’
L187: Mu(t) or mu(X) (as used in Eq 10)?
L201: will be shown in Section 2
Table 2: I got confused by what the sampling covariance is and how it is calculated for deterministic models. Please expand in the text
Eq 15 (and perhaps others). The usual way to present normal distributions is mean and variance, not sd.Â
Fig 5 (bottom right) and others. It always bugs me slightly that the uncertainty in the rate for the present is more unknown when it is the period when we have the most data. Is there a way to solve this with these models? It strikes me that we should be using temporally non-stationary models that allow for far reduced variance (and hence variance on the derivative) to capture the rate of the most recent periods.ÂCitation: https://doi.org/10.5194/egusphere-2024-2183-CC1 - AC3: 'Reply on CC1', Yucheng Lin, 26 Jan 2025
-
RC2: 'Comment on egusphere-2024-2183', Kerry Gallagher, 25 Dec 2024
-
AC1: 'Reply on RC2', Yucheng Lin, 26 Jan 2025
We thank the reviewer for this thoughtful and encouraging feedback. We appreciate the recognition of the study's importance and the effort behind the development of the PaleoSTeHM framework. We have addressed all comments and suggestions in the attached pdf file in blue text.
-
AC1: 'Reply on RC2', Yucheng Lin, 26 Jan 2025
Peer review completion
Journal article(s) based on this preprint
Viewed
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 306 | 103 | 63 | 472 | 16 | 20 |
- HTML: 306
- PDF: 103
- XML: 63
- Total: 472
- BibTeX: 16
- EndNote: 20
Viewed (geographical distribution)
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
Alexander Reedy
Matteo Turilli
Shantenu Jha
Erica L. Ashe
The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.
- Preprint
(7707 KB) - Metadata XML