# High-Resolution Gridded Livestock Projection for Western China Based on Machine Learning

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

^{2}) of 0.75, root mean square error (RMSE) of 9.82 heads/km

^{2}for cattle, and the R

^{2}of 0.73, RMSE of 31.38 heads/km

^{2}for sheep. The accuracy of the RF is slightly lower than the DNN but higher than the SVM. The projection accuracy of the three machine learning models is superior to those of the published Gridded Livestock of the World (GLW) datasets. Consequently, deep learning has the potential to be an effective tool for high-resolution gridded livestock projection by combining geographic and census data.

## 1. Introduction

_{4}and N

_{2}O produced during livestock growth have become the main sources of agricultural greenhouse gas emissions [2,3]. Understanding the spatial distribution of livestock is of great significance for the effective utilization of grassland resources, protection of the ecological environment, and sustainable development of animal husbandry [4]. However, traditional livestock statistics are collected at the administrative unit level, mainly extracted from the “China Statistical Yearbook”. Although census data can be regarded as the approximate “truth” within an administrative unit, it cannot provide enough detailed geographical descriptions of the spatial distribution of livestock. In addition, census data cannot be shared and integrated with grid-based geographic data. The spatialization of census data refers to the projection of statistical values at the administrative level onto the regular grids of a specific scale [5,6]. Therefore, spatializing livestock statistical data and expressing the spatial distribution of livestock on a fine grid scale can be integrated with spatial ecological, social, and economic data on a grid scale to meet the needs of various spatial calculations, models, and analyses.

## 2. Study Area and Data

#### 2.1. Study Area

^{2}. The overall topography characteristics of the study area are high in the south and low in the north. The study area is the leading distribution area of natural pastures and an essential base for the development of animal husbandry in China. The grassland area accounts for 46.15% of the total area of the study area and is the primary land cover type. The proportions of the remaining classes in descending order are 37.60% of unused land, 6.65% of forest land, 5.67% of cultivated land, 3.42% of water area, and 0.50% of construction land.

#### 2.2. Data and Preprocessing

#### 2.2.1. The Gridded Geographic Data

^{−2}) [10], protected areas (areas by stringent conservation measures and tight regulation of human activity), and unsuitable site for pasture (areas with a pasture suitability index of 0). The remaining area after suitable mask in 2000, 2005, 2010, and 2015 accounted for 70.09%, 74.03%, 74.98%, and 74.51% of the total area of the study area, respectively.

#### 2.2.2. Livestock Statistics

## 3. Methodology

#### 3.1. Machine Learning Methods

#### 3.1.1. Support Vector Machine

#### 3.1.2. Random Forest

#### 3.1.3. Deep Neural Network

#### 3.2. Livestock Density Estimation Models

_{10}(n + 1) values to normalize the distribution of the dependent variable. Based on the above independent variables and dependent variables, we obtained a total of 1226 samples (counties), of which 70% were used to train the model and 30% were used to verify the model’s accuracy. The SVM, RF, and DNN based regression models are constructed on the county scale. The basic hypothesis of this study is that there is a robust statistical relationship between livestock density and these environmental predictors at the county-level scale, which in turn could be used to disaggregate livestock census data spatially [11,12]. We apply the trained models to the grid level to obtain livestock density data with a spatial resolution of 1 km based on this assumption. To maintain better consistency between the number of livestock predicted by the developed machine learning models and the census data, we further fine-tuned the estimated results. Finally, the livestock density data were compared with all county-level livestock statistics data to verify the accuracy of the livestock spatialization. The overall process is shown in Figure 2.

#### 3.2.1. Livestock Density Estimation

#### 3.2.2. Livestock Density Adjustment

_{i}is the adjusted value of the grid i, and P

_{j}is the corresponding predicted value of the grid i before adjustment. A

_{j}stands for the statistical value of livestock in municipal administrative district j, and P

_{j}stands for the total predicted gridded livestock of this municipal administrative district.

#### 3.2.3. Performance Evaluation

^{2}) and root mean square error (RMSE), are used to evaluate the performance of the regression models constructed in this study. Their respective formulas are Equations (2) and (3):

_{i}is the statistical livestock density of county i, $\overline{y}$ is an average statistical livestock density of counties, ${\widehat{y}}_{i}$ is the model’s predicted value for county i, and n is the number of samples. It can be seen from the formula that R

^{2}can be negative. Generally speaking, if the predicted value of the developed model is precisely equal to the true value without any error, then R

^{2}is 1. If the explanatory power of the developed model is equivalent to that $\overline{y}$, then R

^{2}is 0. If the explanatory power of the developed model is worse than that $\overline{y}$, R

^{2}is less than 0.

## 4. Results

#### 4.1. Gridded Livestock Distribution Maps

^{2}and RMSE of estimated distribution density of cattle and sheep for each machine learning based livestock spatialization model. In general, the errors of the three models are within acceptable limits. It can be seen from Table 2 that the DNN model has the highest accuracy on the county scale, with its R

^{2}exceeding 0.95 and RMSE is significantly lower than the other two models for both cattle and sheep on the training set. On the test set, the performance of all three machine learning models has some degradation, but DNN is still superior to the other two, with its R

^{2}exceeding 0.73, and RMSE is the smallest of the three models. The accuracy of the RF model is slightly lower than that of the DNN model, and the SVM model performs the worst. In addition, to analyze the estimation performance of the three machine learning models on the 1 km grid scale, we further aggregate the prediction results on the 1 km grid scale to the county scale, and compare them with the census data, as shown in Figure 7. The livestock distribution density estimated by the three machine learning models is very consistent with the census data, which shows that the three machine learning models have good robustness and can provide a stable estimation of livestock distribution density on the grid scale. Moreover, the performance of the three models can still be ranked as DNN > RF > SVM. However, there is no remarkable performance difference between them. For example, theR

^{2}of DNN is 0.75 for cattle and 0.73 for sheep, but the R

^{2}of RF and SVR also reaches 0.74 and 0.73 for cattle, 0.73 and 0.71 for sheep, respectively. In terms of different species, the estimation accuracy of gridded cattle distribution density is higher than that of sheep. The cattle and sheep distribution density has concentrated in 0–20 heads per km

^{2}and 0–100 heads per km

^{2}, respectively. The distribution density of cattle has a slight peak at 20–40 head/km

^{2}.

#### 4.2. Spatiotemporal Changes of Livestock

## 5. Discussion

#### 5.1. Comparison with the Open Access Gridded Livestock Datasets

^{2}of cattle for GLW2 and GLW3 are −1.16 and −0.41, this is significantly lower than the accuracy of the three models developed in this study (R

^{2}exceeds 0.7), when the distribution density values of them are aggregated to the county scale and compared with the census data. Although the accuracy of GLW3 is higher than that of GLW2, it is still difficult to accurately describe the spatial distribution of livestock in six provinces in western China.

^{2}. Although the performance of GLW3 is greatly improved compared with GLW2, with its R

^{2}can reach 0.5, it is still significantly inferior to the three machine learning models developed in this study.

#### 5.2. The Reasonableness of the Hypothesis

#### 5.3. Selection and Contribution of Environmental Factors

## 6. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Acknowledgments

## Conflicts of Interest

## References

- Wang, M. China’s livestock industry development: Achievements, experiences and future trends. Chin. Issues Agric. Econ.
**2018**, 8, 60–70. [Google Scholar] - Olesen, J.; Schelde, K.; Weiske, A.; Weisbjerg, M.; Asman, W.; Djurhuus, J. Modelling greenhouse gas emissions from European conventional and organic dairy farms. Agric. Ecosyst. Environ.
**2006**, 112, 207–220. [Google Scholar] [CrossRef] - Monteny, G.-J.; Bannink, A.; Chadwick, D. Greenhouse gas abatement strategies for animal husbandry. Agric. Ecosyst. Environ.
**2006**, 112, 163–170. [Google Scholar] [CrossRef] - Steinfeld, H.; Gerber, P.; Wassenaar, T.D.; Castel, V.; Rosales, M.; Rosales, M.; de Haan, C. Livestock’s Long Shadow: Environmental Issues and Options; Food & Agriculture Organization: Rome, Italy, 2006. [Google Scholar]
- Dong, N.; Yang, X.; Cai, H. Research progress and perspective on the spatialization of population data. J. Geo-Inf. Sci
**2016**, 18, 1295–1304. [Google Scholar] [CrossRef] - Goodchild, M.F.; Anselin, L.; Deichmann, U. A framework for the areal interpolation of socioeconomic data. Environ. Plan. A
**1993**, 25, 383–397. [Google Scholar] [CrossRef] - Wint, W.; Robinson, T. Gridded Livestock of the World 2007; FAO: Roma, Italy, 2007. [Google Scholar]
- Robinson, T.P.; Wint, G.W.; Conchedda, G.; Van Boeckel, T.P.; Ercoli, V.; Palamara, E.; Cinardi, G.; D’Aietti, L.; Hay, S.I.; Gilbert, M. Mapping the global distribution of livestock. PLoS ONE
**2014**, 9, e96084. [Google Scholar] [CrossRef] [Green Version] - Nicolas, G.; Robinson, T.P.; Wint, G.W.; Conchedda, G.; Cinardi, G.; Gilbert, M. Using random forest to improve the downscaling of global livestock census data. PLoS ONE
**2016**, 11, e0150424. [Google Scholar] [CrossRef] [Green Version] - Gilbert, M.; Nicolas, G.; Cinardi, G.; Van Boeckel, T.P.; Vanwambeke, S.O.; Wint, G.W.; Robinson, T.P. Global distribution data for cattle, buffaloes, horses, sheep, goats, pigs, chickens and ducks in 2010. Sci. Data
**2018**, 5, 180227. [Google Scholar] [CrossRef] [Green Version] - Neumann, K.; Elbersen, B.S.; Verburg, P.H.; Staritsky, I.; Pérez-Soba, M.; de Vries, W.; Rienks, W.A. Modelling the spatial distribution of livestock in Europe. Landsc. Ecol.
**2009**, 24, 1207–1222. [Google Scholar] [CrossRef] - Prosser, D.J.; Wu, J.; Ellis, E.C.; Gale, F.; Van Boeckel, T.P.; Wint, W.; Robinson, T.; Xiao, X.; Gilbert, M. Modelling the distribution of chickens, ducks, and geese in China. Agric. Ecosyst. Environ.
**2011**, 141, 381–389. [Google Scholar] [CrossRef] [Green Version] - Van Boeckel, T.P.; Prosser, D.; Franceschini, G.; Biradar, C.; Wint, W.; Robinson, T.; Gilbert, M. Modelling the distribution of domestic ducks in Monsoon Asia. Agric. Ecosyst. Environ.
**2011**, 141, 373–380. [Google Scholar] [CrossRef] [Green Version] - Qiao, Y.; Zhu, H.; Shao, X.; Zhong, H. Research on Gridding of Livestock Spatial Density Based on Multi-Source Information. China Sci. Technol. Res. Guide
**2017**, 49, 53–59. [Google Scholar] [CrossRef] - Reichstein, M.; Camps-Valls, G.; Stevens, B.; Jung, M.; Denzler, J.; Carvalhais, N. Deep learning and process understanding for data-driven Earth system science. Nature
**2019**, 566, 195–204. [Google Scholar] [CrossRef] - LeCun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature
**2015**, 521, 436–444. [Google Scholar] [CrossRef] - Bailey, D.W.; Stephenson, M.B.; Pittarello, M. Effect of terrain heterogeneity on feeding site selection and livestock movement patterns. Anim. Prod. Sci.
**2015**, 55, 298–308. [Google Scholar] [CrossRef] - Zhou, L.; Xiong, L.-Y. Natural topographic controls on the spatial distribution of poverty-stricken counties in China. Appl. Geogr.
**2018**, 90, 282–292. [Google Scholar] [CrossRef] - Raynor, E.; Gersie, S.; Stephenson, M.; Clark, P.; Spiegal, S.; Boughton, R.; Bailey, D.; Cibils, A.; Smith, B.; Derner, J. Cattle grazing distribution patterns related to topography across diverse rangeland ecosystems of North America. Rangel. Ecol. Manag.
**2021**, 75, 91–103. [Google Scholar] [CrossRef] - Kruska, R.; Reid, R.S.; Thornton, P.K.; Henninger, N.; Kristjanson, P.M. Mapping livestock-oriented agricultural production systems for the developing world. Agric. Syst.
**2003**, 77, 39–63. [Google Scholar] [CrossRef] - Liu, J.; Kuang, W.; Zhang, Z.; Xu, X.; Qin, Y.; Ning, J.; Zhou, W.; Zhang, S.; Li, R.; Yan, C.; et al. Spatiotemporal characteristics, patterns, and causes of land-use changes in China since the late 1980s. J. Geogr. Sci.
**2014**, 24, 195–210. [Google Scholar] [CrossRef] - Liu, J.; Liu, M.; Tian, H.; Zhuang, D.; Zhang, Z.; Zhang, W.; Tang, X.; Deng, X. Spatial and temporal patterns of China’s cropland during 1990–2000: An analysis based on Landsat TM data. Remote Sens. Environ.
**2005**, 98, 442–456. [Google Scholar] [CrossRef] - National Tibetan Plateau Data Center. Available online: http://www.tpdc.ac.cn/zh-hans/data/12e91073-0181-44bf-8308-c50e5bd9a734/ (accessed on 21 December 2020).
- Peng, S. 1-km Monthly Precipitation Dataset for China (1901–2017); A Big Earth Data Platform for Three Poles; National Tibetan Plateau Data Center: Beijing, China, 2020. [Google Scholar]
- Nelson, A. Travel Time to Major Cities: A Global Map of Accessibility; Global Environment Monitoring Unit, Joint Research Centre of the European Commission: Enschede, The Netherlands, 2008. [Google Scholar]
- Weiss, D.J.; Nelson, A.; Gibson, H.S.; Temperley, W.; Peedell, S.; Lieber, A.; Hancher, M.; Poyart, E.; Belchior, S.; Fullman, N.; et al. A global map of travel time to cities to assess inequalities in accessibility in 2015. Nature
**2018**, 553, 333–336. [Google Scholar] [CrossRef] [PubMed] - Resource and Environment Science and Data Center. China Population Spatial Distribution Kilometer Grid Dataset. Available online: https://www.resdc.cn/DOI/DOI.aspx?DOIid=32 (accessed on 10 April 2021).
- Resource and Environment Science and Data Center. China GDP Spatial Distribution Kilometer Grid Data Set. Available online: https://www.resdc.cn/DOI/doi.aspx?DOIid=33 (accessed on 10 April 2021).
- Van Velthuizen, H. Mapping Biophysical Factors that Influence Agricultural Production and Rural Vulnerability; Food & Agriculture Organization: Rome, Italy, 2007. [Google Scholar]
- Vapnik, V. The Nature of Statistical Learning Theory; Springer Science & Business Media: Berlin/Heidelberg, Germany, 1999. [Google Scholar]
- Thomas, S.; Pillai, G.; Pal, K. Prediction of peak ground acceleration using ϵ-SVR, ν-SVR and Ls-SVR algorithm. Geomat. Nat. Hazards Risk
**2017**, 8, 177–193. [Google Scholar] [CrossRef] [Green Version] - Pasolli, L.; Notarnicola, C.; Bruzzone, L. Estimating soil moisture with the support vector regression technique. IEEE Geosci. Remote Sens. Lett.
**2011**, 8, 1080–1084. [Google Scholar] [CrossRef] - Breiman, L. Random forests. Mach. Learn.
**2001**, 45, 5–32. [Google Scholar] [CrossRef] [Green Version] - Scornet, E. Tuning parameters in random forests. ESAIM Proc. Surv.
**2017**, 60, 144–162. [Google Scholar] [CrossRef] [Green Version] - Fang, K.; Wu, J.; Zhu, J.; Xie, B. Research review of random forest method. Stat. Inf. Forum
**2011**, 26, 32–38. [Google Scholar] - Merkel, G.D.; Povinelli, R.J.; Brown, R.H. Short-term load forecasting of natural gas with deep neural network regression. Energies
**2018**, 11, 2008. [Google Scholar] [CrossRef] [Green Version] - Kuwata, K.; Shibasaki, R. Estimating crop yields with deep learning and remotely sensed data. In Proceedings of the 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy, 26–31 July 2015; pp. 858–861. [Google Scholar]
- Zhao, S.; Liu, Y.; Zhang, R.; Fu, B. China’s population spatialization based on three machine learning models. J. Clean. Prod.
**2020**, 256, 120644. [Google Scholar] [CrossRef] - Wang, Y.; Huang, C.; Zhao, M.; Hou, J.; Zhang, Y.; Gu, J. Mapping the Population Density in Mainland China Using NPP/VIIRS and Points-Of-Interest Data Based on a Random Forests Model. Remote Sens.
**2020**, 12, 3645. [Google Scholar] [CrossRef] - Cecchi, G.; Wint, W.; Shaw, A.; Marletta, A.; Mattioli, R.; Robinson, T. Geographic distribution and environmental characterization of livestock production systems in Eastern Africa. Agric. Ecosyst. Environ.
**2010**, 135, 98–110. [Google Scholar] [CrossRef] - Ganskopp, D.; George, M.; Bailey, D.; Borman, M.; Surber, G.; Harris, N. Factors and practices that influence livestock distribution. Univ. Calif. Div. Agric. Nat. Resour.
**2007**, 8217, 20. [Google Scholar] - Lloyd, C.T.; Sorichetta, A.; Tatem, A.J. High resolution global gridded data for use in population studies. Sci. Data
**2017**, 4, 170001. [Google Scholar] [CrossRef] [Green Version] - Hollings, T.; Robinson, A.; van Andel, M.; Jewell, C.; Burgman, M. Species distribution models: A comparison of statistical approaches for livestock and disease epidemics. PLoS ONE
**2017**, 12, e0183626. [Google Scholar] [CrossRef] [Green Version] - Piipponen, J.; Jalava, M.; de Leeuw, J.; Rizayeva, A.; Godde, C.; Herrero, M.; Kummu, M. Global assessment of grassland carrying capacities and relative stocking densities of livestock. Earth Space Sci. Open Arch.
**2021**. [Google Scholar] [CrossRef] - Liu, X.; Huang, J.; Huang, J.; Li, C.; Ding, L.; Meng, W. Estimation of gridded atmospheric oxygen consumption from 1975 to 2018. J. Meteorol. Res.
**2020**, 34, 646–658. [Google Scholar] [CrossRef] - Leng, G.; Hall, J.W. Where is the Planetary Boundary for freshwater being exceeded because of livestock farming? Sci. Total Environ.
**2021**, 760, 144035. [Google Scholar] [CrossRef] - Zhang, L.; Tian, H.; Shi, H.; Pan, S.; Qin, X.; Pan, N.; Dangal, S.R. Methane emissions from livestock in East Asia during 1961−2019. Ecosyst. Health Sustain.
**2021**, 7, 1918024. [Google Scholar] [CrossRef] - El Moustaid, F.; Thornton, Z.; Slamani, H.; Ryan, S.J.; Johnson, L.R. Predicting temperature-dependent transmission suitability of bluetongue virus in livestock. Parasites Vectors
**2021**, 14, 382. [Google Scholar] [CrossRef]

**Figure 3.**Cattle distribution in six provinces of Western China. The first column is the cattle distribution density obtained from the county level census, and the second to fourth columns are the density at the 1 km scale estimated by SVR, RF, and DNN, respectively. The first to fourth rows indicate 2000, 2005, 2010, and 2015, respectively.

**Figure 4.**Sheep distribution in six provinces of western China. The first column is the sheep distribution density obtained from the county level census, and the second to fourth columns are the density at the 1 km scale estimated by SVR, RF, and DNN, respectively. The first to fourth rows indicate 2000, 2005, 2010, and 2015, respectively.

**Figure 5.**Enlarged spatial detail distribution of cattle for two randomly selected small local regions A and B. (

**a**–

**d**) are the land use situation and the spatialized cattle results of the SVM, RF, and DNN models of region A in 2015. (

**e**–

**h**) are the land use situation and the spatialized cattle results of the SVM, RF, and DNN models of region B in 2015.

**Figure 6.**Enlarged spatial detail distribution of sheep for two randomly selected small local regions A and B. (

**a**–

**d**) are the land use situation and the spatialized sheep results of the SVM, RF, and DNN models of region A in 2015. (

**e**–

**h**) are the land use situation and the spatialized sheep results of the SVM, RF, and DNN models of region B in 2015.

**Figure 7.**Accuracy of the livestock spatialization results. The distribution density of (

**a**) cattle and (

**b**) sheep estimated by the model on the 1 km scale was aggregated to the county scale and compared with the census data.

**Figure 8.**Spatiotemporal changes of cattle based on the DNN estimation. (

**a**–

**c**) represent 2000 to 2005, 2005 to 2010, and 2010 to 2015, respectively. The bar charts show the statistical value of cattle in each province.

**Figure 9.**Spatiotemporal changes of sheep based on the DNN estimation. (

**a**–

**c**) represent 2000 to 2005, 2005 to 2010, and 2010 to 2015, respectively. The bar charts show the statistical value of cattle in each province.

**Figure 10.**The scatter diagram of grided distribution density aggregated to the county scale and census data for cattle. (

**a**) SVR; (

**b**) RF; (

**c**) DNN; (

**d**) GLW2; and (

**e**) GLW3. The red line is the linear regression line, and the dotted line is the 1:1 line.

**Figure 11.**The scatter diagram of grided distribution density aggregated to the county scale and census data for sheep. (

**a**) SVR; (

**b**) RF; (

**c**) DNN; (

**d**) GLW2; and (

**e**) GLW3. The red line is the linear regression line, and the dotted line is the 1:1 line.

**Figure 14.**Correlation between environmental factors and density of cattle and sheep. The shape direction of the ellipse in the upper triangular area represents the positive or negative of the correlation, the color is the level of the corresponding correlation, and the lower triangular area is the value of the corresponding correlation coefficient.

**Figure 15.**Importance of environmental factors influencing the spatial distribution of cattle and sheep.

**Table 1.**The geographic data and livestock statistics used for generating gridded livestock distribution.

Type | Variables | Time ^{1} | Source | Initial Data Declaration |
---|---|---|---|---|

Environmental factors | Grassland coverage | 2000–2015 | Chinese Academy of Sciences Resource and Environmental Science Data Center (http://www.resdc.cn, accessed on 10 March 2021) | 100 m |

Arable land coverage | 2000–2015 | 100 m | ||

Forest land coverage | 2000–2015 | 100 m | ||

Desert coverage | 2000–2015 | 100 m | ||

NDVI | 2000–2015 | Geospatial Data Cloud (http://www.gscloud.cn, accessed on 19 March 2021) | 500 m | |

Elevation | 2000 | National Tibetan Plateau Data Center (http://data.tpdc.ac.cn, accessed on 21 December 2020) | 1000 m | |

Slope | 2000 | 1000 m | ||

Daytime surface temperature | 2000–2015 | Geospatial Data Cloud (http://www.gscloud.cn, accessed on 19 March 2021) | 1000 m | |

Precipitation | 2000–2015 | National Tibetan Plateau Data Center (http://data.tpdc.ac.cn, accessed on 25 March 2021) | 1000 m | |

Distance to river | 2000–2015 | Open Street Map (https://www.openstreetmap.org, accessed on 7 April 2021) | shapefile | |

Travel time to major cities | 2000, 2015 | Nelson A. D. et al., D. J. Weiss et al. | 1000 m | |

Population grid data | 2000–2015 | Resource and Environment Science and Data Center (https://www.resdc.cn, accessed on 10 April 2021) | 1000 m | |

GDP grid data | 2000–2015 | 1000 m | ||

Unsuitable areas | Permanent water | 2000–2015 | Chinese Academy of Sciences Resource and Environmental Science Data Center (http://www.resdc.cn, accessed on 10 March 2021) | 100 m |

Urban cores | 2000–2015 | Resource and Environment Science and Data Center (https://www.resdc.cn, accessed on 10 April 2021) | 1000 m | |

Protected areas | 2000–2015 | World Database of Protected Areas (WDPA) (https://www.protectedplanet.net/country/CHN, accessed on 14 April 2021) | shapefile | |

Pasture suitability | 2005 | United Nations Food and Agriculture Organization (https://data.apps.fao.org/map/catalog, accessed on 15 April 2021) | 10,000 m | |

Census | Stock data of cattle | 2000–2015 | China Statistical Yearbooks (http://www.stats.gov.cn/tjsj/pcsj/, accessed on 27 November 2020) | County |

Stock data of sheep | 2000–2015 | County |

^{1}Five-year intervals.

Species | Model | Training Set | Test Set | ||
---|---|---|---|---|---|

R^{2} | RMSE | R^{2} | RMSE | ||

Cattle | SVM | 0.50 | 14.86 | 0.54 | 13.21 |

RF | 0.92 | 5.82 | 0.74 | 9.57 | |

DNN | 0.95 | 4.73 | 0.75 | 8.98 | |

Sheep | SVM | 0.55 | 43.38 | 0.52 | 52.65 |

RF | 0.93 | 19.59 | 0.72 | 34.58 | |

DNN | 0.96 | 14.71 | 0.73 | 33.97 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Li, X.; Hou, J.; Huang, C.
High-Resolution Gridded Livestock Projection for Western China Based on Machine Learning. *Remote Sens.* **2021**, *13*, 5038.
https://doi.org/10.3390/rs13245038

**AMA Style**

Li X, Hou J, Huang C.
High-Resolution Gridded Livestock Projection for Western China Based on Machine Learning. *Remote Sensing*. 2021; 13(24):5038.
https://doi.org/10.3390/rs13245038

**Chicago/Turabian Style**

Li, Xianghua, Jinliang Hou, and Chunlin Huang.
2021. "High-Resolution Gridded Livestock Projection for Western China Based on Machine Learning" *Remote Sensing* 13, no. 24: 5038.
https://doi.org/10.3390/rs13245038