Decomposition Factor Analysis Based on Virtual Experiments throughout Bayesian Optimization for Compost-Degradable Polymers
Round 1
Reviewer 1 Report
Dear Authors,
Your manuscript is well written and its topic has scientific significance. My comment is the following.
Line 79: Please replace the word "with" with the word "which".
Author Response
Your manuscript is well written and its topic has scientific significance. My comment is the following.
[Response. 1-1]
Thank you for reviewing our manuscript.
Line 79: Please replace the word "with" with the word "which".
[Response. 1-2]
The word “with” in line 81 (line 79 in previous manuscript) has been replaced with “which” as per your suggestion.
Author Response File: 
Author Response.docx
Reviewer 2 Report
The manuscript is an interesting approach to studying the degradation of biopolymers. The paper is well written and presented and my main concerns are related to the terminology and scope as outlined below with some other comments.
Line 14, there are numerous other factors preventing the adoption of biodegradable polymers. Degradation control is much less of a concern to society and consumers. It is perhaps a much greater concern to facilities that compost these materials.
Line 41: polymers cannot be described as “environmentally conscious”, please clarify.
Figure 1 caption has too much detail. The method is practically given here.
The introduction falls short in that there is discussion of environmental degradation and composting which are very different. The terms degradation and biodegradation refer to very different mechanisms which are not considered in the scope of this work.
The methods describe the use of “soil” purchased from a supplier but there is inadequate characterization of this substrate. It is unclear whether this material could be regarded as compost which would be expected to contain a wide range of organic materials and microorganisms.
In general, the methods and discussion are adequately presented. My main concern is clarifying the scope of the work which is clearly a degradation study rather than biodegradation. As such, the title should not contain the terms “compost-degradable”, rather bio-derived polymers or biopolymers.
Author Response
The manuscript is an interesting approach to studying the degradation of biopolymers. The paper is well written and presented and my main concerns are related to the terminology and scope as outlined below with some other comments.
[Response. 2-1]
Thank you for reviewing our manuscript.
Line 14, there are numerous other factors preventing the adoption of biodegradable polymers. Degradation control is much less of a concern to society and consumers. It is perhaps a much greater concern to facilities that compost these materials.
[Response. 2-2]
As you pointed out, several other factors hinder the widespread use of biodegradable plastics. Because our objective was to elucidate the relationship between degradation and complex degradation factors, we have modified the Abstract to focus on the complexity of degradation factors, but not “biodegradation”.
Lines 13–17
“Bio-based polymers have been considered as an alternative to oil-based materials for their “carbon-neutral” environmentally degrative features. However, degradation is a complex system in which environmental factors and preparation conditions are involved, and the relationship between degradation and these factors/conditions has not yet been clarified. Moreover, an efficient system that addresses multiple degradation factors has not been developed for practical use.”
Line 41: polymers cannot be described as “environmentally conscious”, please clarify.
[Response. 2-3]
We intended to say that “biodegradable plastics are relatively environmentally friendly among polymers.” As you pointed out, it was a confusing expression; hence, we have rewritten it to focus on PLA. Furthermore, the Introduction section in the manuscript has been significantly revised as follows:
Lines 33–73
“Plastics, which are lightweight and stable, are essential materials that support our daily lives most widely in the form of containers, such as plastic bottles and synthetic fibers. By contrast, owing to their high stability, pollution due to plastics disposal has become an apparent problem in many countries worldwide [1,2]. Furthermore, “carbon-neutral” bio-based polymers, such as polylactic acid (PLA), polybutylene succinate (PBS), and polycaprolactone (PCL), have become a focus in the era of biorefinery materials as an alternative to oil-based materials [3,4]. Here, we focused on PLA, which is one of the most used bio-based plastics. It is known that the degradation rate of PLA changes depending on the amount of moisture, temperature, and hydrogen ion concentration (pH) in the surrounding environment [5]; moreover, degradation factors are intricately entwined, including environmental factors and preparation conditions, and the relationship between degradation and these factors/conditions has not yet been clarified. The elucidation was considered to be extremely meaningful in predicting the degree of degradation. Moreover, a computational degradation predictive method could overcome the time and costs constraints to experimentally demonstrate bio-based plastics decomposition.
We measured how to comprehensively get the data for the sample and surrounding environment to solve the relationship between these complex systems, and data science analysis could be useful for this process [6-11]. In measurement method, solid-state nuclear magnetic resonance (NMR) reflects both crystalline and amorphous structures in chemical shifts [12,13]; in particular, PLA emits broad signals for the amorphous component and sharp signals for the crystalline component in cross-polarization and magic angle spinning (13C-CP/MAS) spectra [14,15]. Therefore, we decided to use solid-state NMR as the analysis method. In the analysis method, we focused on Bayesian optimization. Bayesian optimization has already been used in materials science [16-19] and is an effective method, particularly for complex systems, such as preparation conditions, chemical composition, and microstructure. Moreover, this analysis method can be applied to a small number of experiments, as is typical of the design of experiments, and is considered suitable for the rapid prediction of the degree of degradation. Therefore, we decided to construct a degradation prediction model, mainly based on Bayesian optimization. Further, because bio-based plastic degradation is also greatly affected by the surrounding environment, we decided to obtain the environmental conditions and incorporate them into the dataset. The degradation prediction model focusing on the surrounding environment is a new attempt.
In this study, we performed degradation experiments on PLA, which is the most common bio-based plastic; the results were used to construct a model that can predict the degree of degradation while considering the surrounding environment and degradation factors and their contribution rates. Furthermore, the optimum decomposition degree, various analytical values, and experimental conditions were explored using virtual experiments that combine the decomposition degree predictive model with Bayesian optimization.”
Figure 1 caption has too much detail. The method is practically given here.
[Response. 2-4]
Because there were some overlaps with the description of the method, the description of Figure 1 has been omitted, and its position was changed.
Lines 172–176
“Figure 1. Concept of real and virtual degradable experiments in this study. Actual decomposition experiments were performed to obtain experimental conditions and various analytical data (left). The optimum decomposition degree, various analytical values, and experimental conditions were explored by virtual experiments combining with a predictive model and Bayesian optimization (right).”
The introduction falls short in that there is discussion of environmental degradation and composting which are very different. The terms degradation and biodegradation refer to very different mechanisms which are not considered in the scope of this work.
[Response. 2-5]
The term “degradation” is used instead of “biodegradation” in the text because the experiments were performed in a short period of time and the effects of physicochemical hydrolysis are expected to be significant too.
The methods describe the use of “soil” purchased from a supplier but there is inadequate characterization of this substrate. It is unclear whether this material could be regarded as compost which would be expected to contain a wide range of organic materials and microorganisms.
[Response. 2-6]
“Commercial compost” was used for compost disassembly for household kitchen waste. The purchase source is shown in the text as follows:
Line 84–87
“The degradation experiment was performed by burying the samples in containers filled with commercial compost along with targets for compost degradation of raw waste, which was purchased from Eco Clean Co., Ltd (https://www.gotonet.co.jp/products/detail.php?product_id=8710491)”
In general, the methods and discussion are adequately presented. My main concern is clarifying the scope of the work which is clearly a degradation study rather than biodegradation. As such, the title should not contain the terms “compost-degradable”, rather bio-derived polymers or biopolymers.
[Response. 2-7]
We performed degradation experiments of biodegradable plastics in a composting environment. Therefore, we believe that the term compost-degradable (degradable in compost) is appropriate.
Author Response File: Author Response.docx
Reviewer 3 Report
The manuscript “Decomposition factor analysis based on virtual experiments throughout Bayesian optimization for compost-degradable polymers” consider construction and application of a decomposition degree predictive model, which is based on experimental data, analytical results and application of machine learning methods, such as Bayesian optimization. The computational costs of the Bayesian optimization are reduced by principal component analysis (PCA) based dimension reduction.
The considered application is the degradation of the biodegradable plastic in the compost environment. The measurements were provided by several spectrometers. The machine learning part by random forest / tree libraries and R software package.
The manuscript is scientific relevant and well written. The presented results are meaningful. The considered topic is application relevant and relevant to society.
Questions / Remarks:
Sec. 2.4: It would be helpful to the reader, if the authors describe more precisely which type and options of Bayesian optimization / random forest algorithms were used to obtain the results presented in the manuscript.
Author Response
The manuscript “Decomposition factor analysis based on virtual experiments throughout Bayesian optimization for compost-degradable polymers” consider construction and application of a decomposition degree predictive model, which is based on experimental data, analytical results and application of machine learning methods, such as Bayesian optimization. The computational costs of the Bayesian optimization are reduced by principal component analysis (PCA) based dimension reduction.
The considered application is the degradation of the biodegradable plastic in the compost environment. The measurements were provided by several spectrometers. The machine learning part by random forest / tree libraries and R software package.
The manuscript is scientific relevant and well written. The presented results are meaningful. The considered topic is application relevant and relevant to society.
[Response. 3-1]
Thank you for reviewing our manuscript.
Questions / Remarks:
Sec. 2.4: It would be helpful to the reader, if the authors describe more precisely which type and options of Bayesian optimization / random forest algorithms were used to obtain the results presented in the manuscript.
[Response. 3-2]
We have added the texts and description of type and options of Bayesian optimization/random forest algorithms to the manuscript as follows:
Line 177–191
“PCA, machine learning, and Bayesian optimization were performed using the stats library, caret library [23], and rBayesianOptimization library [24] in R software. The method name “rf” in the caret library was chosen to use the RF algorithm. The hyperparameter “mtry” as randomly selected predictors in the RF algorithm was tuned by grid searching, and the method name “xgbLinear” in the caret library was chosen to use the XGBoost algorithm. The hyperparameters “nrounds” as boosting iterations, “lambda” as L2 regularization, “alpha” as L1 regularization, and “eta” as learning rate in the XGBoost algorithm were tuned by grid searching. In Bayesian optimization, the expected improvement was used as an acquisition function type. The Gaussian process updated the acquisition function. The search range was from −2 times the minimum value to 2 times the maximum value of each explanatory variable. Ten points as an initial variable were chosen randomly to sample the target function before Bayesian optimization fitting the Gaussian process. The iterative calculation of Bayesian optimization was based on 20 iterations. The program, including PCA, Bayesian optimization, and machine learning, and its details are available at http://dmar.riken.jp/NMRinformatics/.”
Author Response File: Author Response.docx
Round 2
Reviewer 2 Report
The authors have thoroughly and adequately addressed my comments and concerns.
