Comments on abstract, title, references

Abstract Despite the exciting research proposal, the abstract still needs to summarize the connection with the sound basis source and the plant's stress mentioned. Also, clarify the selection criteria of ultrasonic ranges on small plants should be explained.

Title The term "remotely" used in the title indicates that probably, a type of sporadic detectable sounds, suggesting that the findings are in a constantly changing dynamic. Then, if a variant nature exists in sound phenomena, the authors could highlight this aspect and improve the findings' relevance and help the readers' comprehension.

references I respectfully suggest to include current references that mention precise irrigation and economic implications

Comments on introduction/background

The authors refer to studies related to plants physiology and the possible association with airborne sounds and responses concerning the introduction. However, an appropriate, some sentences like the one indicated in paragraph 70, “We, therefore, set to examine whether plants emit informative airborne sounds, which may serve as potential signals or cues to their environment. Here we show for the first time that plants indeed emit airborne sounds, which can be detected from several meters away” is not supported by literature and any study performed. In this regard, authors should include what is unknown about plants and sound in recent literature, including some gene expression and frequency sensitivity for elongation.
Furthermore, if the research question is addressed from a machine learning process, the specific condition for tomato or tobacco still needs to highlight big data.

Comments on methodology

The methodology for experimental needs to explain quite more details about the background sound management. Therefore, answering the following point in the text could improve the manuscript quality:

1. The authors should mention the bandwidth range on which the airborne cues are proposed to be measured (referring to similar studies). 2. The criteria to choose the evaluation of these types of conditions on the plants could be defined. Also, include a section that justified why those types of mechanical damage were selected for the study or to sustain a specific reason.
2. The phytoacoustics term has been proposed before by the same research group. Therefore, the authors can highlight how and why they came up with this new term and quote the study before.
3. Authors can consider the primary consideration for established the time of measurement duration of sound recordings.
4. The "number of sounds per hour" considered a "unit" needs a formal description or cite if that unit has been assessed before in acoustic terms. 6If authors contemplated using more reference microphones to guarantee the same signal reception on different devices during experiments; it should also be mentioned and the frequency response of them.

Comments on data and results

The authors can justify why they consider it relevant to show the accuracy of sound classification achieved by different feature extraction methods. The difference between the data used to sustain that the vector machine and the classification method of feature extraction MFCC needs support.

According to Figure 1, the acoustic terms “number of sounds” need support to be considered a valid variable. The convolution neural network used to distinguish “greenhouse noises” does not show if the sound was filtered. Figure 2 could improve the descriptiveness in this aspect.

The paragraph 125 shows, "The mean peak intensity of the sounds emitted by cut tomato plants was 130 65.6±0.2 dBSPL at 10 cm with a mean peak frequency of 57.3±0.7 kHz (frequency with maximal energy), and the mean intensity of the sounds emitted by cut tobacco plants was 63.3±0.2 dBSPL at 10.0 cm distance with a mean frequency of 57.8±0.7 kHz". The study could clarify that dB SPL is a logarithmic function, meaning that a difference of 2.3 dB SPL between plants exposed to the same source of stress (cut) represents a partially explained biophysical phenomenon.

Comments on discussion and conclusions

Further research questions are addressed adequately as potential study objects for additional experimentation. Also, alternative explanations should be included in the evaluation. Specifically, based on plant conditions related to specific frequency ranges. Finding that plants could associate sounds from the environment, but from themselves depending on changes in their immediate neighbors or their structures as physiological adjustments to drought or cut results fascinating when learning algorism works as a predictable source of data of how plants could respond. However, measurement and instrumentation details need explanation related to the affinity of instruments and the evaluated variables. I consider that experimental design for two types of conditions and the differences found are pioneer bioacoustics results. It directly impacts my field, showing that sounds could vary among species and bring new research possibilities to find more physiological responses from biophysical signals.

Major points in the article which needs clarification, refinement, reanalysis, rewrites, and/or additional information and suggestions for what could be done to improve the article.

1. The term "remotely" in the title is not further described along with the text.
2. The ability to distinguish between drought-stressed and control plants requires support on data, considering other physiological aspects that prove the physiological conditions that are referenced.
3. The difference between the data used to sustain that the vector machine and the classification method of feature extraction MFCC need support.

Minor points like figures/tables not being mentioned in the text, a missing reference, typos, and other inconsistencies. 1. Some references need to be included