the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
ChinaCropSM1km: a fine 1km daily Soil Moisture dataset for Crop drylands across China during 1993–2018
- 1Academy of Disaster Reduction and Emergency Management Minsitry of Emergency Management & Ministry of Education, School of National Safety and Emergency Management, Beijing Normal University, Beijing 100875
- 2Key Laboratory of Land Surface Pattern and Simulation, Institute of Geographical Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
- 3College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China
- 4Natural Resources Institute Finland (Luke), FI-00790 Helsinki, Finland
- 1Academy of Disaster Reduction and Emergency Management Minsitry of Emergency Management & Ministry of Education, School of National Safety and Emergency Management, Beijing Normal University, Beijing 100875
- 2Key Laboratory of Land Surface Pattern and Simulation, Institute of Geographical Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
- 3College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China
- 4Natural Resources Institute Finland (Luke), FI-00790 Helsinki, Finland
Abstract. Soil moisture (SM) is a key variable of regional hydrological cycle and has important applications for water resource and agricultural drought management. Various global soil moisture products have been mostly retrieved from microwave remote sensing data. However, there is currently rare spatially explicit and time-continuous soil moisture information with a high resolution at a nation scale. Here we generated a 1km soil moisture dataset for stable crop drylands in China (ChinaCropSM1km) over 1993−2018 through random forest (RF) algorithm, based on numerous in situ daily observations of soil moisture. We used independently in situ observations (181327 samples) from the Agricultural Meteorological Stations (AMS) across China for training (164202 samples) and others for testing (17125 samples). An irrigation module was firstly developed according to crop type (i.e. wheat, maize), soil depth (0–10 cm, 10–20 cm) and phenology. We produced four daily datasets separately by crop type and soil depth, and their accuracy is all satisfactory (wheat r 0.93, ubRMSE 0.033 m3 m–3; maize r 0.93, ubRMSE 0.035 m3 m–3). The spatio-temporal resolutions and accuracy of ChinaCropSM1km are significantly better than those of global soil moisture products (e.g. r increased by 116 %, ubRMSE decreased by 64 %), including the global remote-sensing-based surface soil moisture dataset (RSSSM) and the European Space Agency (ESA) Climate Change Initiative (CCI) SM. The approach developed in our study could be applied into other regions and crops in the world, and our improved datasets are very valuable for many studies and field managements such as agriculture drought monitoring and crop yield forecasting. The data are published in Zenodo at https://zenodo.org/record/6834530 (wheat0–10) (Cheng et al., 2022a), https://zenodo.org/record/6822591 (wheat10–20) (Cheng et al., 2022b), https://zenodo.org/record/6822581 (maize0–10) (Cheng et al., 2022c) and https://zenodo.org/record/6820166 (mazie10–20) (Cheng et al., 2022d).
-
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
(1726 KB)
-
Supplement
(1109 KB)
-
The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.
- Preprint
(1726 KB) -
Supplement
(1109 KB) - BibTeX
- EndNote
Journal article(s) based on this preprint
Fei Cheng et al.
Interactive discussion
Status: closed
-
EC1: 'Comment on essd-2022-254', Hao Shi, 04 Sep 2022
Please carefully check the citations and references. For example, the references repeat with each other in lines 345-360.
-
AC1: 'Reply on EC1', zhao zhang, 05 Sep 2022
Many thanks for your careful check. We have followed your advice and checked the all citations and references. We have deleted duplicate references (Line 345-360) and modified citations in the text (Line 51-53, 54-56, 130-131, 254-255).
1) Line 51-53: As one part of the Climate Change Initiative (CCI), the European Space Agency (ESA) published a long-term surface SM dataset, and the latest version (v06.1) covered the period of 1978–2020 (https://www.esa-soilmoisture-cci.org/, last access: 10 Apr. 2022) (Dorigo et al., 2017a; Gruber et al., 2019; Preimesberger et al., 2021).
we have modified the citations to “As one part of the Climate Change Initiative (CCI), the European Space Agency (ESA) published a long-term surface SM dataset, and the latest version (v06.1) covered the period of 1978–2020 (https://www.esa-soilmoisture-cci.org/, last access: 10 Apr. 2022) (Dorigo et al., 2017; Gruber et al., 2019; Preimesberger et al., 2021).”.
2) Line 54-56: The ESA CCI SM products are consistent with the observed values at some grassland and farmland sites in China (Liu et al., 2011; Albergel et al., 2013; Dorigo et al., 55 2015, 2017b), however, they have a coarse spatial resolution (~27 km) and lots of coverage gaps (Llamas et al., 2020; Guevara et al., 2021).
we have modified the citations to “The ESA CCI SM products are consistent with the observed values at some grassland and farmland sites in China (Liu et al., 2011; Albergel et al., 2013; Dorigo et al., 2015, 2017), however, they have a coarse spatial resolution (~27 km) and lots of coverage gaps (Llamas et al., 2020; Guevara et al., 2021).”.
3) Line 130-131：We used the v05.2 product for comparison because of its advantages comparing with active/passive products (Liu et al., 2012; Dorigo et al., 2017c).
we have modified the citations to “We used the v05.2 product for comparison because of its advantages comparing with active/passive products (Liu et al., 2012; Dorigo et al., 2017).”.
3) Line 254-255：We ascribed such improvement partly into some corrections based on in situ observations for ESA 255 CCI SM (Dorigo et al., 2017b).
we have modified the citations to “We ascribed such improvement partly into some corrections based on in situ observations for ESA CCI SM (Dorigo et al., 2017).”.
4) Line 345-360：Dorigo, W., Wagner, W., Albergel, C., Albrecht, F., Balsamo, G., Brocca, L., Chung, D., Ertl, M., Forkel, M., Gruber, A., Haas, E., Hamer, P. D., Hirschi, M., Ikonen, J., de Jeu, R., Kidd, R., Lahoz, W., Liu, Y. Y., Miralles, D., Mistelbauer, T., Nicolai-Shaw, N., Parinussa, R., Pratola, C., Reimer, C., van der Schalie, R., Seneviratne, S. I., Smolander, T., and Lecomte, P.: ESA CCI Soil Moisture for improved Earth system understanding: State-of-the art and future directions, Remote Sensing of Environment, 203, 185–215, https://doi.org/10.1016/j.rse.2017.07.001, 2017a.
Dorigo, W., Wagner, W., Albergel, C., Albrecht, F., Balsamo, G., Brocca, L., Chung, D., Ertl, M., Forkel, M., Gruber, A., Haas, E., Hamer, P. D., Hirschi, M., Ikonen, J., de Jeu, R., Kidd, R., Lahoz, W., Liu, Y. Y., Miralles, D., Mistelbauer, T., Nicolai-Shaw, N., Parinussa, R., Pratola, C., Reimer, C., van der Schalie, R., Seneviratne, S. I., Smolander, T., and Lecomte, P.: ESA CCI Soil Moisture for improved Earth system understanding: State-of-the art and future directions, Remote Sensing of Environment, 203, 185–215, https://doi.org/10.1016/j.rse.2017.07.001, 2017b.
Dorigo, W., Wagner, W., Albergel, C., Albrecht, F., Balsamo, G., Brocca, L., Chung, D., Ertl, M., Forkel, M., Gruber, A., Haas, E., Hamer, P. D., Hirschi, M., Ikonen, J., de Jeu, R., Kidd, R., Lahoz, W., Liu, Y. Y., Miralles, D., Mistelbauer, T., Nicolai-Shaw, N., Parinussa, R., Pratola, C., Reimer, C., van der Schalie, R., Seneviratne, S. I., Smolander, T., and Lecomte, P.: ESA CCI Soil Moisture for improved Earth system understanding: State-of-the art and future directions, Remote Sensing of Environment, 203, 185–215, https://doi.org/10.1016/j.rse.2017.07.001, 2017c.
we have modified the references to “Dorigo, W., Wagner, W., Albergel, C., Albrecht, F., Balsamo, G., Brocca, L., Chung, D., Ertl, M., Forkel, M., Gruber, A., Haas, E., Hamer, P. D., Hirschi, M., Ikonen, J., de Jeu, R., Kidd, R., Lahoz, W., Liu, Y. Y., Miralles, D., Mistelbauer, T., Nicolai-Shaw, N., Parinussa, R., Pratola, C., Reimer, C., van der Schalie, R., Seneviratne, S. I., Smolander, T., and Lecomte, P.: ESA CCI Soil Moisture for improved Earth system understanding: State-of-the art and future directions, Remote Sensing of Environment, 203, 185–215, https://doi.org/10.1016/j.rse.2017.07.001, 2017.”.
-
AC1: 'Reply on EC1', zhao zhang, 05 Sep 2022
-
RC1: 'Comment on essd-2022-254', Anonymous Referee #1, 09 Sep 2022
I was very impressed by such valuable daily SM for more than 20 years over the whole mainland of China. Comparing with quantities of public products retrieved from remote sensing or downscaling into fine resolution, Chinacropland really open a new window for us to provide key parameters on earth observations. Irrigation practices do play more significances on crop production in China, especially for dryland crop. Therefore, no any doubt will be shown on the values of irrigation sub-model. Such novelty imply a potential way for applying irrigation sub-model into other areas and crops in the world. The study is fallen closely within the scope of ESSD. However, the authors should consider my several concerns below before their submission being accepted
(1) I am wondering how they obtain the crop dryland maps. For wheat or maize, it seem to me the location is constant. I need more detailed information to better understand their study.
(2) I do not think RF is a new method to retrieve SM. That is to say, more interesting findings have ascribed from combining irrigation module into SM estimation model. However, the authors have not specified the point. I am looking forward to more information on it, e.g. the accuracy comparison between with irrigation module and without it.(3) Deeper and more extent discussions will further expand the reputation and influence of their study.
(4) Generally, the English writing is Ok. But typo can be observed sometimes, a careful check should be conducted throughout their manuscript.
-
AC2: 'Reply on RC1', zhao zhang, 03 Oct 2022
Dear Reviewer,
Thank you a lot for the constructive comments. We have responded to every question, indicating exactly how we addressed each concern.
The point-to-point responses to the comments are attached to the supplement in PDF format.
Thank you again for your reviewing and the insightful comments.
Sincerely,
Fei Cheng on behalf of all Co-Authors
-
AC2: 'Reply on RC1', zhao zhang, 03 Oct 2022
-
RC2: 'Comment on essd-2022-254', Anonymous Referee #2, 12 Sep 2022
This study provides a longer term soil moisture dataset (ChinaCropSM1km) for crop drylands across mainland of China. ChinaCropSM1km perform better than public product in both higher accuracy and more details (daily, more soil layers) by using machine learning technology. Such soil moisture dataset with higher resolutions is very valuable for the studies on crop model, yield estimation, and climate change impact assessment. Moreover, their methodology is robust, and their interesting results were well interpreted. The irrigation module is a novel way to improve highly moisture estimation. Therefore, I recommend it can be accepted after a minor revision.
Comments and suggestions:
- There is a problem with the resolution. The ground observation data is point measurement data, how to match the resolution of 1km? Please explain this in the manuscript.
- Section 2.1. The authors pointed out that the study area is dominated by dryland crops (i.e. wheat and maize) in China, how was the Chinacropland layer defined in Figure 1 according to the annual crop harvested area in mainland China from 2000 to 2015? please describe the details.
- In (1), the author judges the irrigation factors by comparing the observed soil moisture and the soil moisture evaluation index (SMI) according to the corresponding soil depth and phenology of crops. However, I notice that the SMI in Table 2 is a range, rather than an exact number. Please give reasonable explanation for this.
- In section 2.3.2, considering the new SM product has been derived by integrating the irrigation module into SM model, it is better to evaluate accuracy of the module (irrigation factor forecasting model) and supply such important information into new edition.
- Some typos are found in manuscript, and check manuscript carefully and correct them. e.g. Line143: delete ‘in China’.
- Figure 2 should be improved. Currently, some labels are too vague to clearly identify.
- Please modify the line widths in Table 2.
- Line257: insert blank between two words. ‘Figure8’ -> ‘Figure 8’.
- Figure S5 was not used in the main text, please cite it in main text or delete it from supplemental material.
-
AC3: 'Reply on RC2', zhao zhang, 03 Oct 2022
Dear Reviewer,
Thank you a lot for the constructive comments. We have responded to every question, indicating exactly how we addressed each concern.
The point-to-point responses to the comments are attached to the supplement in PDF format.
Thank you again for your reviewing and the insightful comments.
Sincerely,
Fei Cheng on behalf of all Co-Authors
-
RC3: 'Comment on essd-2022-254', Anonymous Referee #3, 16 Oct 2022
This is an interesting effort in developing the SM product for crop dryland, which has potential for various applications. The paper is well written and organized. Taking the CIR as a predictor seems to be a useful way to predict SM in crop dryland. However, I have some concerns as following. Please pay more attention on the comments about line 174-175.
Why only mapping SM for dryland, not rice?
Line 110-115: there are two sources of FCï¼ which one is used?
Line 120: the short name “AMS” is used only one time. Consider full name. In addition, what is R4, R5 and R16? And it should not be calculated only for AMS but for each cell, as a predictor.
Line 171: Grammar error. Not a complete sentence.
Line 174-175: It should not be random splitting because SM of different time from the same site may be highly correlated. This will give a higher performance for the model. Instead, the splitting should be based on sites, i.e., data from a site should be all in the training set or all in test set. Note that the model is predicting unknown locations based on the observing sites, and the spatial interpolation ability should be evaluated by the site-based splitting.
Line 185: How many times do you run the model to get the importance, as the importance will be different each time. It should take the average importance of dozens of runs like 100.
Fig.6 and 7ï¼ what are the different boxes stand for?
Section 3.5ï¼ I do not think this comparison is fare. The evaluation using the test data for Cropland should be used instead of all in situ data because the model used them to establish leading to an independent evaluation.
-
AC4: 'Reply on RC3', zhao zhang, 11 Nov 2022
Dear Reviewer,
Thank you a lot for the constructive comments. We have responded to every question, indicating exactly how we addressed each concern.
The point-to-point responses to the comments are attached to the supplement in PDF format.
Thank you again for your reviewing and the insightful comments.
Sincerely,
Fei Cheng on behalf of all Co-Authors
-
AC4: 'Reply on RC3', zhao zhang, 11 Nov 2022
Peer review completion
Interactive discussion
Status: closed
-
EC1: 'Comment on essd-2022-254', Hao Shi, 04 Sep 2022
Please carefully check the citations and references. For example, the references repeat with each other in lines 345-360.
-
AC1: 'Reply on EC1', zhao zhang, 05 Sep 2022
Many thanks for your careful check. We have followed your advice and checked the all citations and references. We have deleted duplicate references (Line 345-360) and modified citations in the text (Line 51-53, 54-56, 130-131, 254-255).
1) Line 51-53: As one part of the Climate Change Initiative (CCI), the European Space Agency (ESA) published a long-term surface SM dataset, and the latest version (v06.1) covered the period of 1978–2020 (https://www.esa-soilmoisture-cci.org/, last access: 10 Apr. 2022) (Dorigo et al., 2017a; Gruber et al., 2019; Preimesberger et al., 2021).
we have modified the citations to “As one part of the Climate Change Initiative (CCI), the European Space Agency (ESA) published a long-term surface SM dataset, and the latest version (v06.1) covered the period of 1978–2020 (https://www.esa-soilmoisture-cci.org/, last access: 10 Apr. 2022) (Dorigo et al., 2017; Gruber et al., 2019; Preimesberger et al., 2021).”.
2) Line 54-56: The ESA CCI SM products are consistent with the observed values at some grassland and farmland sites in China (Liu et al., 2011; Albergel et al., 2013; Dorigo et al., 55 2015, 2017b), however, they have a coarse spatial resolution (~27 km) and lots of coverage gaps (Llamas et al., 2020; Guevara et al., 2021).
we have modified the citations to “The ESA CCI SM products are consistent with the observed values at some grassland and farmland sites in China (Liu et al., 2011; Albergel et al., 2013; Dorigo et al., 2015, 2017), however, they have a coarse spatial resolution (~27 km) and lots of coverage gaps (Llamas et al., 2020; Guevara et al., 2021).”.
3) Line 130-131：We used the v05.2 product for comparison because of its advantages comparing with active/passive products (Liu et al., 2012; Dorigo et al., 2017c).
we have modified the citations to “We used the v05.2 product for comparison because of its advantages comparing with active/passive products (Liu et al., 2012; Dorigo et al., 2017).”.
3) Line 254-255：We ascribed such improvement partly into some corrections based on in situ observations for ESA 255 CCI SM (Dorigo et al., 2017b).
we have modified the citations to “We ascribed such improvement partly into some corrections based on in situ observations for ESA CCI SM (Dorigo et al., 2017).”.
4) Line 345-360：Dorigo, W., Wagner, W., Albergel, C., Albrecht, F., Balsamo, G., Brocca, L., Chung, D., Ertl, M., Forkel, M., Gruber, A., Haas, E., Hamer, P. D., Hirschi, M., Ikonen, J., de Jeu, R., Kidd, R., Lahoz, W., Liu, Y. Y., Miralles, D., Mistelbauer, T., Nicolai-Shaw, N., Parinussa, R., Pratola, C., Reimer, C., van der Schalie, R., Seneviratne, S. I., Smolander, T., and Lecomte, P.: ESA CCI Soil Moisture for improved Earth system understanding: State-of-the art and future directions, Remote Sensing of Environment, 203, 185–215, https://doi.org/10.1016/j.rse.2017.07.001, 2017a.
Dorigo, W., Wagner, W., Albergel, C., Albrecht, F., Balsamo, G., Brocca, L., Chung, D., Ertl, M., Forkel, M., Gruber, A., Haas, E., Hamer, P. D., Hirschi, M., Ikonen, J., de Jeu, R., Kidd, R., Lahoz, W., Liu, Y. Y., Miralles, D., Mistelbauer, T., Nicolai-Shaw, N., Parinussa, R., Pratola, C., Reimer, C., van der Schalie, R., Seneviratne, S. I., Smolander, T., and Lecomte, P.: ESA CCI Soil Moisture for improved Earth system understanding: State-of-the art and future directions, Remote Sensing of Environment, 203, 185–215, https://doi.org/10.1016/j.rse.2017.07.001, 2017b.
Dorigo, W., Wagner, W., Albergel, C., Albrecht, F., Balsamo, G., Brocca, L., Chung, D., Ertl, M., Forkel, M., Gruber, A., Haas, E., Hamer, P. D., Hirschi, M., Ikonen, J., de Jeu, R., Kidd, R., Lahoz, W., Liu, Y. Y., Miralles, D., Mistelbauer, T., Nicolai-Shaw, N., Parinussa, R., Pratola, C., Reimer, C., van der Schalie, R., Seneviratne, S. I., Smolander, T., and Lecomte, P.: ESA CCI Soil Moisture for improved Earth system understanding: State-of-the art and future directions, Remote Sensing of Environment, 203, 185–215, https://doi.org/10.1016/j.rse.2017.07.001, 2017c.
we have modified the references to “Dorigo, W., Wagner, W., Albergel, C., Albrecht, F., Balsamo, G., Brocca, L., Chung, D., Ertl, M., Forkel, M., Gruber, A., Haas, E., Hamer, P. D., Hirschi, M., Ikonen, J., de Jeu, R., Kidd, R., Lahoz, W., Liu, Y. Y., Miralles, D., Mistelbauer, T., Nicolai-Shaw, N., Parinussa, R., Pratola, C., Reimer, C., van der Schalie, R., Seneviratne, S. I., Smolander, T., and Lecomte, P.: ESA CCI Soil Moisture for improved Earth system understanding: State-of-the art and future directions, Remote Sensing of Environment, 203, 185–215, https://doi.org/10.1016/j.rse.2017.07.001, 2017.”.
-
AC1: 'Reply on EC1', zhao zhang, 05 Sep 2022
-
RC1: 'Comment on essd-2022-254', Anonymous Referee #1, 09 Sep 2022
I was very impressed by such valuable daily SM for more than 20 years over the whole mainland of China. Comparing with quantities of public products retrieved from remote sensing or downscaling into fine resolution, Chinacropland really open a new window for us to provide key parameters on earth observations. Irrigation practices do play more significances on crop production in China, especially for dryland crop. Therefore, no any doubt will be shown on the values of irrigation sub-model. Such novelty imply a potential way for applying irrigation sub-model into other areas and crops in the world. The study is fallen closely within the scope of ESSD. However, the authors should consider my several concerns below before their submission being accepted
(1) I am wondering how they obtain the crop dryland maps. For wheat or maize, it seem to me the location is constant. I need more detailed information to better understand their study.
(2) I do not think RF is a new method to retrieve SM. That is to say, more interesting findings have ascribed from combining irrigation module into SM estimation model. However, the authors have not specified the point. I am looking forward to more information on it, e.g. the accuracy comparison between with irrigation module and without it.(3) Deeper and more extent discussions will further expand the reputation and influence of their study.
(4) Generally, the English writing is Ok. But typo can be observed sometimes, a careful check should be conducted throughout their manuscript.
-
AC2: 'Reply on RC1', zhao zhang, 03 Oct 2022
Dear Reviewer,
Thank you a lot for the constructive comments. We have responded to every question, indicating exactly how we addressed each concern.
The point-to-point responses to the comments are attached to the supplement in PDF format.
Thank you again for your reviewing and the insightful comments.
Sincerely,
Fei Cheng on behalf of all Co-Authors
-
AC2: 'Reply on RC1', zhao zhang, 03 Oct 2022
-
RC2: 'Comment on essd-2022-254', Anonymous Referee #2, 12 Sep 2022
This study provides a longer term soil moisture dataset (ChinaCropSM1km) for crop drylands across mainland of China. ChinaCropSM1km perform better than public product in both higher accuracy and more details (daily, more soil layers) by using machine learning technology. Such soil moisture dataset with higher resolutions is very valuable for the studies on crop model, yield estimation, and climate change impact assessment. Moreover, their methodology is robust, and their interesting results were well interpreted. The irrigation module is a novel way to improve highly moisture estimation. Therefore, I recommend it can be accepted after a minor revision.
Comments and suggestions:
- There is a problem with the resolution. The ground observation data is point measurement data, how to match the resolution of 1km? Please explain this in the manuscript.
- Section 2.1. The authors pointed out that the study area is dominated by dryland crops (i.e. wheat and maize) in China, how was the Chinacropland layer defined in Figure 1 according to the annual crop harvested area in mainland China from 2000 to 2015? please describe the details.
- In (1), the author judges the irrigation factors by comparing the observed soil moisture and the soil moisture evaluation index (SMI) according to the corresponding soil depth and phenology of crops. However, I notice that the SMI in Table 2 is a range, rather than an exact number. Please give reasonable explanation for this.
- In section 2.3.2, considering the new SM product has been derived by integrating the irrigation module into SM model, it is better to evaluate accuracy of the module (irrigation factor forecasting model) and supply such important information into new edition.
- Some typos are found in manuscript, and check manuscript carefully and correct them. e.g. Line143: delete ‘in China’.
- Figure 2 should be improved. Currently, some labels are too vague to clearly identify.
- Please modify the line widths in Table 2.
- Line257: insert blank between two words. ‘Figure8’ -> ‘Figure 8’.
- Figure S5 was not used in the main text, please cite it in main text or delete it from supplemental material.
-
AC3: 'Reply on RC2', zhao zhang, 03 Oct 2022
Dear Reviewer,
Thank you a lot for the constructive comments. We have responded to every question, indicating exactly how we addressed each concern.
The point-to-point responses to the comments are attached to the supplement in PDF format.
Thank you again for your reviewing and the insightful comments.
Sincerely,
Fei Cheng on behalf of all Co-Authors
-
RC3: 'Comment on essd-2022-254', Anonymous Referee #3, 16 Oct 2022
This is an interesting effort in developing the SM product for crop dryland, which has potential for various applications. The paper is well written and organized. Taking the CIR as a predictor seems to be a useful way to predict SM in crop dryland. However, I have some concerns as following. Please pay more attention on the comments about line 174-175.
Why only mapping SM for dryland, not rice?
Line 110-115: there are two sources of FCï¼ which one is used?
Line 120: the short name “AMS” is used only one time. Consider full name. In addition, what is R4, R5 and R16? And it should not be calculated only for AMS but for each cell, as a predictor.
Line 171: Grammar error. Not a complete sentence.
Line 174-175: It should not be random splitting because SM of different time from the same site may be highly correlated. This will give a higher performance for the model. Instead, the splitting should be based on sites, i.e., data from a site should be all in the training set or all in test set. Note that the model is predicting unknown locations based on the observing sites, and the spatial interpolation ability should be evaluated by the site-based splitting.
Line 185: How many times do you run the model to get the importance, as the importance will be different each time. It should take the average importance of dozens of runs like 100.
Fig.6 and 7ï¼ what are the different boxes stand for?
Section 3.5ï¼ I do not think this comparison is fare. The evaluation using the test data for Cropland should be used instead of all in situ data because the model used them to establish leading to an independent evaluation.
-
AC4: 'Reply on RC3', zhao zhang, 11 Nov 2022
Dear Reviewer,
Thank you a lot for the constructive comments. We have responded to every question, indicating exactly how we addressed each concern.
The point-to-point responses to the comments are attached to the supplement in PDF format.
Thank you again for your reviewing and the insightful comments.
Sincerely,
Fei Cheng on behalf of all Co-Authors
-
AC4: 'Reply on RC3', zhao zhang, 11 Nov 2022
Peer review completion
Journal article(s) based on this preprint
Fei Cheng et al.
Data sets
ChinaCropSM1km: a fine 1km daily Soil Moisture dataset for Crop drylands across China during 1993–2018 Fei Cheng, Zhao Zhang, Huimin Zhuang, Jichong Han, Yuchuan Luo, Juan Cao, Liangliang Zhang, Jing Zhang, Fulu Tao, & Jialu Xu. https://doi.org/10.5281/zenodo.6834530
ChinaCropSM1km: a fine 1km daily Soil Moisture dataset for Crop drylands across China during 1993–2018 Fei Cheng, Zhao Zhang, Huimin Zhuang, Jichong Han, Yuchuan Luo, Juan Cao, Liangliang Zhang, Jing Zhang, Fulu Tao, & Jialu Xu. https://doi.org/10.5281/zenodo.6822591
ChinaCropSM1km: a fine 1km daily Soil Moisture dataset for Crop drylands across China during 1993–2018 Fei Cheng, Zhao Zhang, Huimin Zhuang, Jichong Han, Yuchuan Luo, Juan Cao, Liangliang Zhang, Jing Zhang, Fulu Tao, & Jialu Xu. https://doi.org/10.5281/zenodo.6820166
ChinaCropSM1km: a fine 1km daily Soil Moisture dataset for Crop drylands across China during 1993–2018 Fei Cheng, Zhao Zhang, Huimin Zhuang, Jichong Han, Yuchuan Luo, Juan Cao, Liangliang Zhang, Jing Zhang, Fulu Tao, & Jialu Xu. https://doi.org/10.5281/zenodo.6822581
Fei Cheng et al.
Viewed
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 566 | 168 | 25 | 759 | 39 | 5 | 7 |
- HTML: 566
- PDF: 168
- XML: 25
- Total: 759
- Supplement: 39
- BibTeX: 5
- EndNote: 7
Viewed (geographical distribution)
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.
- Preprint
(1726 KB) - Metadata XML
-
Supplement
(1109 KB) - BibTeX
- EndNote