# Geospatial Artificial Intelligence (GeoAI) and Satellite Imagery Fusion for Soil Physical Property Predicting

^{1}

^{2}

^{3}

^{4}

^{*}

## Abstract

**:**

^{2}: 0.995), sand (R

^{2}: 0.992), and silt (R

^{2}: 0.987), as indicated by the R

^{2}index. The RF algorithm identified MRVBF, LST, and B7 as the most influential parameters for clay, sand, and silt prediction, respectively, underscoring the significance of remote sensing, topography, and climate. Our integrated GeoAI-satellite imagery approach provides valuable tools for monitoring soil degradation, optimizing agricultural irrigation, and assessing soil quality. This methodology has significant potential to advance precision agriculture and land resource management practices.

## 1. Introduction

## 2. Materials and Methods

#### 2.1. Study Area

#### 2.2. Soil Samples

^{2}and the precise coordinates of the soil samples determined using the Global Positioning System (GPS). In total, 317 soil samples were distributed across various landcover classes (Figure 2). Specifically, 73% of the samples belonged to agricultural land, 13% to range land, 9% to uncovered plain, 3% to residential areas, 1% to forest, and 1% to water bodies. Out of all the soil samples, approximately 75% were situated at altitudes below 200 m, while the remaining 25% were located at altitudes above 200 m.

#### 2.3. Environmental Parameters

#### 2.3.1. RS Parameters

#### 2.3.2. Topographic Parameters

_{s}is the catchment area index and β is the slope angle [48].

#### 2.3.3. Climatic Parameters

#### 2.4. Prediction Models

#### 2.4.1. RF Algorithm

#### 2.4.2. CNN

_{j}of the convolution layer, where ${x}_{i}$ is the ith feature of the input vector of the CNN network, W

_{ij}is the weight between ${x}_{i}$ and the jth kernel of the convolution layer with bias b, and k and n are the number of kernels and the number of features of the input vector to the convolution layer, respectively [58]. The activation function f can be sigmoid, tanh, or ReLU, among others.

#### 2.4.3. CNN-RF

#### 2.5. Models Evaluation

^{2}) (Equations (4)–(6)). Lower MSE and RMSE values indicate a higher modeling accuracy. R

^{2}illustrates the goodness of fit between the data and the regression model. The value of R

^{2}ranges from 0 to 1, with values closer to 1 indicating better model performance [60,61].

#### 2.6. K-Fold Cross-Validation

#### 2.7. Workflow for Soil Texture Prediction

^{2}, box plot, and Taylor diagram.

## 3. Results

#### 3.1. Correlation Analysis

#### 3.2. Feature Importance

#### 3.3. Model Development

#### 3.4. Comparison of Prediction Models

^{2}, were employed, and the evaluation results are presented in Table 6. The results indicate that for clay, the CNN, RF, and CNN-RF algorithms yielded MSE values of 0.00016%

^{2}, 0.00079%

^{2}, and 0.00005%

^{2}, RMSE values of 0.013%, 0.028%, and 0.007%, and R

^{2}values of 0.981, 0.910, and 0.995 in the training phase, and MSE values of 0.00038%

^{2}, 0.00407%

^{2}, and 0.00010%

^{2}, RMSE values of 0.019%, 0.064%, 0.010%, and R

^{2}values of 0.966, 0.636, 0.982 in the testing phase. Regarding sand, the CNN model produced MSE values of 0.00029%

^{2}and 0.00046%

^{2}, RMSE values of 0.017% and 0.022%, and R

^{2}values of 0.928 and 0.908 in the training and testing phases, respectively. Additionally, for this property, the RF algorithm generated MSE values of 0.00034%

^{2}and 0.00135%

^{2}, RMSE values of 0.018% and 0.037%, and R

^{2}values of 0.917 and 0.683, while the combined CNN-RF model produced MSE values of 0.00003%

^{2}and 0.00007%

^{2}, RMSE values of 0.006% and 0.008%, and R

^{2}values of 0.992 and 0.976 in the training and testing phases, respectively. Furthermore, for silt, the CNN model yielded MSE, RMSE, and R

^{2}values of 0.00024%

^{2}, 0.016%, and 0.920, respectively, during the training phase, and 0.00040%

^{2}, 0.020%, and 0.913, respectively, during the testing phase. Moreover, the RF algorithm generated MSE values of 0.00022%

^{2}and 0.00060%

^{2}, RMSE values of 0.00060% and 0.024%, and R

^{2}values of 0.935 and 0.676 for this property during the testing and training phases, respectively. In comparison, the combined CNN-RF model produced MSE, RMSE, and R

^{2}values of 0.00004%

^{2}, 0.006, and 0.987 during the training phase and 0.00009%

^{2}, 0.010%, and 0.980 during the testing phase, respectively.

#### 3.5. Spatial Prediction of Soil Properties

## 4. Discussion

#### 4.1. Analysis of Parameters Affecting Soil Texture

#### 4.2. Model Comparison and Analysis

#### 4.3. Strengths and Weaknesses

## 5. Conclusions and Recommendations

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## Appendix A

## References

- Elramady, H.; Brevik, E.C.; Elsakhawy, T.; Omara, A.E.-D.; Amer, M.M.; Abowaly, M.; El-Henawy, A.; Prokisch, J. Soil and Humans: A Comparative and A Pictorial Mini-Review. Egypt. J. Soil Sci.
**2022**, 62, 101–122. [Google Scholar] [CrossRef] - Tahat, M.M.; Alananbeh, K.M.; Othman, Y.A.; Leskovar, D.I. Soil health and sustainable agriculture. Sustainability
**2020**, 12, 4859. [Google Scholar] [CrossRef] - Polakowski, C.; Ryżak, M.; Sochan, A.; Beczek, M.; Mazur, R.; Bieganowski, A. Particle size distribution of various soil materials measured by laser diffraction—The problem of reproducibility. Minerals
**2021**, 11, 465. [Google Scholar] [CrossRef] - Liakos, L.; Panagos, P. Challenges in the Geo-Processing of Big Soil Spatial Data. Land
**2022**, 11, 2287. [Google Scholar] [CrossRef] - Shanmugapriya, P.; Rathika, S.; Ramesh, T.; Janaki, P. Applications of remote sensing in agriculture—A Review. Int. J. Curr. Microbiol. Appl. Sci
**2019**, 8, 2270–2283. [Google Scholar] [CrossRef] - Shafapour Tehrany, M.; Shabani, F.; Neamah Jebur, M.; Hong, H.; Chen, W.; Xie, X. GIS-based spatial prediction of flood prone areas using standalone frequency ratio, logistic regression, weight of evidence and their ensemble techniques. Geomat. Nat. Hazards Risk
**2017**, 8, 1538–1561. [Google Scholar] [CrossRef] - Mousavi, S.Z.; Kavian, A.; Soleimani, K.; Mousavi, S.R.; Shirzadi, A. GIS-based spatial prediction of landslide susceptibility using logistic regression model. Geomat. Nat. Hazards Risk
**2011**, 2, 33–50. [Google Scholar] [CrossRef] - Zeraatpisheh, M.; Garosi, Y.; Owliaie, H.R.; Ayoubi, S.; Taghizadeh-Mehrjardi, R.; Scholten, T.; Xu, M. Improving the spatial prediction of soil organic carbon using environmental covariates selection: A comparison of a group of environmental covariates. Catena
**2022**, 208, 105723. [Google Scholar] [CrossRef] - Ye, C.-M.; Wei, R.-L.; Ge, Y.-G.; Li, Y.; Junior, J.M.; Li, J. GIS-based spatial prediction of landslide using road factors and random forest for Sichuan-Tibet Highway. J. Mt. Sci.
**2022**, 19, 461–476. [Google Scholar] [CrossRef] - Dobarco, M.R.; Orton, T.G.; Arrouays, D.; Lemercier, B.; Paroissien, J.-B.; Walter, C.; Saby, N.P. Prediction of soil texture using descriptive statistics and area-to-point kriging in Region Centre (France). Geoderma Reg.
**2016**, 7, 279–292. [Google Scholar] [CrossRef] - Liao, K.; Xu, S.; Wu, J.; Zhu, Q. Spatial estimation of surface soil texture using remote sensing data. Soil Sci. Plant Nutr.
**2013**, 59, 488–500. [Google Scholar] [CrossRef] - Costa, J.J.F.; Giasson, E.; da Silva, E.B.; Coblinski, J.A.; Tiecher, T. Use of color parameters in the grouping of soil samples produces more accurate predictions of soil texture and soil organic carbon. Comput. Electron. Agric.
**2020**, 177, 105710. [Google Scholar] [CrossRef] - Wadoux, A.M.-C. Using deep learning for multivariate mapping of soil with quantified uncertainty. Geoderma
**2019**, 351, 59–70. [Google Scholar] [CrossRef] - Ließ, M.; Glaser, B.; Huwe, B. Uncertainty in the spatial prediction of soil texture: Comparison of regression tree and Random Forest models. Geoderma
**2012**, 170, 70–79. [Google Scholar] [CrossRef] - Gholizadeh, A.; Borůvka, L.; Saberioon, M.; Vašát, R. A memory-based learning approach as compared to other data mining algorithms for the prediction of soil texture using diffuse reflectance spectra. Remote Sens.
**2016**, 8, 341. [Google Scholar] [CrossRef] - Curcio, D.; Ciraolo, G.; D’Asaro, F.; Minacapilli, M. Prediction of soil texture distributions using VNIR-SWIR reflectance spectroscopy. Procedia Environ. Sci.
**2013**, 19, 494–503. [Google Scholar] [CrossRef] - Wuest, T.; Weimer, D.; Irgens, C.; Thoben, K.-D. Machine learning in manufacturing: Advantages, challenges, and applications. Prod. Manuf. Res.
**2016**, 4, 23–45. [Google Scholar] [CrossRef] - Ray, S. A quick review of machine learning algorithms. In Proceedings of the 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), Faridabad, India, 14–16 February 2019; pp. 35–39. [Google Scholar]
- Barzegar, R.; Aalami, M.T.; Adamowski, J. Coupling a hybrid CNN-LSTM deep learning model with a Boundary Corrected Maximal Overlap Discrete Wavelet Transform for multiscale Lake water level forecasting. J. Hydrol.
**2021**, 598, 126196. [Google Scholar] [CrossRef] - Zhang, Y.; Le, J.; Liao, X.; Zheng, F.; Li, Y. A novel combination forecasting model for wind power integrating least square support vector machine, deep belief network, singular spectrum analysis and locality-sensitive hashing. Energy
**2019**, 168, 558–572. [Google Scholar] [CrossRef] - Alygizakis, N.; Giannakopoulos, T.; Τhomaidis, N.S.; Slobodnik, J. Detecting the sources of chemicals in the Black Sea using non-target screening and deep learning convolutional neural networks. Sci. Total Environ.
**2022**, 847, 157554. [Google Scholar] [CrossRef] - Taghizadeh-Mehrjardi, R.; Khademi, H.; Khayamim, F.; Zeraatpisheh, M.; Heung, B.; Scholten, T. A comparison of model averaging techniques to predict the spatial distribution of soil properties. Remote Sens.
**2022**, 14, 472. [Google Scholar] [CrossRef] - Feng, D.; Chen, H. A small samples training framework for deep Learning-based automatic information extraction: Case study of construction accident news reports analysis. Adv. Eng. Inform.
**2021**, 47, 101256. [Google Scholar] [CrossRef] - Azadnia, R.; Jahanbakhshi, A.; Rashidi, S.; Bazyar, P. Developing an automated monitoring system for fast and accurate prediction of soil texture using an image-based deep learning network and machine vision system. Measurement
**2022**, 190, 110669. [Google Scholar] [CrossRef] - Taghizadeh-Mehrjardi, R.; Mahdianpari, M.; Mohammadimanesh, F.; Behrens, T.; Toomanian, N.; Scholten, T.; Schmidt, K. Multi-task convolutional neural networks outperformed random forest for mapping soil particle size fractions in central Iran. Geoderma
**2020**, 376, 114552. [Google Scholar] [CrossRef] - Garajeh, M.K.; Malakyar, F.; Weng, Q.; Feizizadeh, B.; Blaschke, T.; Lakes, T. An automated deep learning convolutional neural network algorithm applied for soil salinity distribution mapping in Lake Urmia, Iran. Sci. Total Environ.
**2021**, 778, 146253. [Google Scholar] [CrossRef] - Celik, M.F.; Isik, M.S.; Yuzugullu, O.; Fajraoui, N.; Erten, E. Soil Moisture Prediction from Remote Sensing Images Coupled with Climate, Soil Texture and Topography via Deep Learning. Remote Sens.
**2022**, 14, 5584. [Google Scholar] [CrossRef] - Baskakov, D.; Arseniev, D. On the computational complexity of deep learning algorithms. In Proceedings of the International Scientific Conference on Telecommunications, Computing and Control: TELECCON 2019, St. Petersburg, Russia, 18–19 November 2019; pp. 343–356. [Google Scholar]
- Bejani, M.M.; Ghatee, M. A systematic review on overfitting control in shallow and deep neural networks. Artif. Intell. Rev.
**2021**, 54, 6391–6438. [Google Scholar] [CrossRef] - Bailly, A.; Blanc, C.; Francis, É.; Guillotin, T.; Jamal, F.; Wakim, B.; Roy, P. Effects of dataset size and interactions on the prediction performance of logistic regression and deep learning models. Comput. Methods Programs Biomed.
**2022**, 213, 106504. [Google Scholar] [CrossRef] - Khan, M.; Jan, B.; Farman, H.; Ahmad, J.; Farman, H.; Jan, Z. Deep Learning Methods and Applications; Springer: Berlin/Heidelberg, Germany, 2019; pp. 31–42. [Google Scholar]
- Adhaityar, B.Y.; Sahara, D.P.; Pratama, C.; Wibowo, A.; Heliani, L.S. Multi-Target Regression Using Convolutional Neural Network-Random Forests (CNN-RF) for Early Earthquake Warning System. In Proceedings of the 2021 9th International Conference on Information and Communication Technology (ICoICT), Yogyakarta, Indonesia, 3–5 August 2021; pp. 31–36. [Google Scholar]
- Zhao, X.; Yu, B.; Liu, Y.; Chen, Z.; Li, Q.; Wang, C.; Wu, J. Estimation of poverty using random forest regression with multi-source data: A case study in Bangladesh. Remote Sens.
**2019**, 11, 375. [Google Scholar] [CrossRef] - Costache, R.; Arabameri, A.; Moayedi, H.; Pham, Q.B.; Santosh, M.; Nguyen, H.; Pandey, M.; Pham, B.T. Flash-flood potential index estimation using fuzzy logic combined with deep learning neural network, naïve Bayes, XGBoost and classification and regression tree. Geocarto Int.
**2022**, 37, 6780–6807. [Google Scholar] [CrossRef] - Fang, Z.; Wang, Y.; Peng, L.; Hong, H. Integration of convolutional neural network and conventional machine learning classifiers for landslide susceptibility mapping. Comput. Geosci.
**2020**, 139, 104470. [Google Scholar] [CrossRef] - Zhou, X.; Lu, P.; Zheng, Z.; Tolliver, D.; Keramati, A. Accident prediction accuracy assessment for highway-rail grade crossings using random forest algorithm compared with decision tree. Reliab. Eng. Syst. Saf.
**2020**, 200, 106931. [Google Scholar] [CrossRef] - Kwak, G.-H.; Park, C.-W.; Lee, K.-D.; Na, S.-I.; Ahn, H.-Y.; Park, N.-W. Potential of hybrid CNN-RF model for early crop mapping with limited input data. Remote Sens.
**2021**, 13, 1629. [Google Scholar] [CrossRef] - Nijhawan, R.; Das, J.; Balasubramanian, R. A hybrid CNN+ random forest approach to delineate debris covered glaciers using deep features. J. Indian Soc. Remote Sens.
**2018**, 46, 981–989. [Google Scholar] [CrossRef] - Bouyoucos, G.J. Hydrometer method improved for making particle size analyses of soils 1. Agron. J.
**1962**, 54, 464–465. [Google Scholar] [CrossRef] - Fathololoumi, S.; Vaezi, A.R.; Alavipanah, S.K.; Ghorbani, A.; Saurette, D.; Biswas, A. Improved digital soil mapping with multitemporal remotely sensed satellite data fusion: A case study in Iran. Sci. Total Environ.
**2020**, 721, 137703. [Google Scholar] [CrossRef] - Shahriari, M.; Delbari, M.; Afrasiab, P.; Pahlavan-Rad, M.R. Predicting regional spatial distribution of soil texture in floodplains using remote sensing data: A case of southeastern Iran. Catena
**2019**, 182, 104149. [Google Scholar] [CrossRef] - Khanal, S.; Fulton, J.; Klopfenstein, A.; Douridas, N.; Shearer, S. Integration of high resolution remotely sensed data and machine learning techniques for spatial prediction of soil properties and corn yield. Comput. Electron. Agric.
**2018**, 153, 213–225. [Google Scholar] [CrossRef] - Yang, H.; Zhang, X.; Xu, M.; Shao, S.; Wang, X.; Liu, W.; Wu, D.; Ma, Y.; Bao, Y.; Zhang, X. Hyper-temporal remote sensing data in bare soil period and terrain attributes for digital soil mapping in the Black soil regions of China. Catena
**2020**, 184, 104259. [Google Scholar] [CrossRef] - Forkuor, G.; Hounkpatin, O.K.; Welp, G.; Thiel, M. High resolution mapping of soil properties using remote sensing variables in south-western Burkina Faso: A comparison of machine learning and multiple linear regression models. PLoS ONE
**2017**, 12, e0170478. [Google Scholar] [CrossRef] - Dharumarajan, S.; Hegde, R.; Singh, S. Spatial prediction of major soil properties using Random Forest techniques–A case study in semi-arid tropics of South India. Geoderma Reg.
**2017**, 10, 154–162. [Google Scholar] [CrossRef] - Shafizadeh-Moghadam, H.; Minaei, F.; Talebi-khiyavi, H.; Xu, T.; Homaee, M. Synergetic use of multi-temporal Sentinel-1, Sentinel-2, NDVI, and topographic factors for estimating soil organic carbon. Catena
**2022**, 212, 106077. [Google Scholar] [CrossRef] - Sahabiev, I.; Smirnova, E.; Giniyatullin, K. Spatial Prediction of Agrochemical Properties on the Scale of a Single Field Using Machine Learning Methods Based on Remote Sensing Data. Agronomy
**2021**, 11, 2266. [Google Scholar] [CrossRef] - Razavi-Termeh, S.V.; Seo, M.; Sadeghi-Niaraki, A.; Choi, S.-M. Application of genetic algorithm in optimization parallel ensemble-based machine learning algorithms to flood susceptibility mapping using radar satellite imagery. Sci. Total Environ.
**2023**, 873, 162285. [Google Scholar] [CrossRef] [PubMed] - Breiman, L. Random forests. Mach. Learn.
**2001**, 45, 5–32. [Google Scholar] [CrossRef] - Razavi-Termeh, S.V.; Sadeghi-Niaraki, A.; Farhangi, F.; Choi, S.-M. COVID-19 risk mapping with considering socio-economic criteria using machine learning algorithms. Int. J. Environ. Res. Public Health
**2021**, 18, 9657. [Google Scholar] [CrossRef] [PubMed] - Sahani, N.; Ghosh, T. GIS-based spatial prediction of recreational trail susceptibility in protected area of Sikkim Himalaya using logistic regression, decision tree and random forest model. Ecol. Inform.
**2021**, 64, 101352. [Google Scholar] [CrossRef] - Farhangi, F.; Sadeghi-Niaraki, A.; Razavi-Termeh, S.V.; Choi, S.-M. Evaluation of tree-based machine learning algorithms for accident risk mapping caused by driver lack of alertness at a national scale. Sustainability
**2021**, 13, 10239. [Google Scholar] [CrossRef] - Segal, M.R. Machine Learning Benchmarks and Random Forest Regression; Kluwer Academic Publisher: Dordrecht, The Netherlands, 2004. [Google Scholar]
- Gu, J.; Wang, Z.; Kuen, J.; Ma, L.; Shahroudy, A.; Shuai, B.; Liu, T.; Wang, X.; Wang, G.; Cai, J. Recent advances in convolutional neural networks. Pattern Recognit.
**2018**, 77, 354–377. [Google Scholar] [CrossRef] - Li, Z.; Liu, F.; Yang, W.; Peng, S.; Zhou, J. A survey of convolutional neural networks: Analysis, applications, and prospects. IEEE Trans. Neural Netw. Learn. Syst.
**2021**, 33, 6999–7019. [Google Scholar] [CrossRef] [PubMed] - Wang, Y.; Fang, Z.; Hong, H. Comparison of convolutional neural networks for landslide susceptibility mapping in Yanshan County, China. Sci. Total Environ.
**2019**, 666, 975–993. [Google Scholar] [CrossRef] [PubMed] - Ng, W.; Minasny, B.; McBratney, A. Convolutional neural network for soil microplastic contamination screening using infrared spectroscopy. Sci. Total Environ.
**2020**, 702, 134723. [Google Scholar] [CrossRef] - Zhang, Z.; Tian, J.; Huang, W.; Yin, L.; Zheng, W.; Liu, S. A haze prediction method based on one-dimensional convolutional neural network. Atmosphere
**2021**, 12, 1327. [Google Scholar] [CrossRef] - Elbaz, K.; Shaban, W.M.; Zhou, A.; Shen, S.-L. Real time image-based air quality forecasts using a 3D-CNN approach with an attention mechanism. Chemosphere
**2023**, 333, 138867. [Google Scholar] [CrossRef] - Razavi-Termeh, S.V.; Sadeghi-Niaraki, A.; Choi, S.-M. Spatial modeling of asthma-prone areas using remote sensing and ensemble machine learning algorithms. Remote Sens.
**2021**, 13, 3222. [Google Scholar] [CrossRef] - Farahani, M.; Razavi-Termeh, S.V.; Sadeghi-Niaraki, A. A spatially based machine learning algorithm for potential mapping of the hearing senses in an urban environment. Sustain. Cities Soc.
**2022**, 80, 103675. [Google Scholar] [CrossRef] - Taylor, K.E. Summarizing multiple aspects of model performance in a single diagram. J. Geophys. Res. Atmos.
**2001**, 106, 7183–7192. [Google Scholar] [CrossRef] - Potter, K.; Hagen, H.; Kerren, A.; Dannenmann, P. Methods for presenting statistical information: The box plot. In Proceedings of the VLUDS, 2006. pp. 97–106. Available online: https://sci.utah.edu/~kpotter/publications/potter-2006-MPSI.pdf (accessed on 20 July 2023).
- Lopez-del Rio, A.; Nonell-Canals, A.; Vidal, D.; Perera-Lluna, A. Evaluation of cross-validation strategies in sequence-based binding prediction using deep learning. J. Chem. Inf. Model.
**2019**, 59, 1645–1657. [Google Scholar] [CrossRef] [PubMed] - Gallant, J.C.; Dowling, T.I. A multiresolution index of valley bottom flatness for mapping depositional areas. Water Resour. Res.
**2003**, 39, 1347. [Google Scholar] [CrossRef] - Jones, E.J.; Filippi, P.; Wittig, R.; Fajardo, M.; Pino, V.; McBratney, A.B. Mapping soil slaking index and assessing the impact of management in a mixed agricultural landscape. Soil
**2021**, 7, 33–46. [Google Scholar] [CrossRef] - Zhao, W.; Li, Z.-L. Sensitivity study of soil moisture on the temporal evolution of surface temperature over bare surfaces. Int. J. Remote Sens.
**2013**, 34, 3314–3331. [Google Scholar] [CrossRef] - Şekertekin, A.; Kutoglu, Ş.; Kaya, S.; Marangoz, A. Analysing the effects of different land cover types on land surface temperature using satellite data. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci.
**2015**, 40, 665–667. [Google Scholar] [CrossRef] - Przybylek, P. Application of Near-Infrared Spectroscopy to Measure the Water Content in Liquid Dielectrics. Energies
**2022**, 15, 5907. [Google Scholar] [CrossRef] - Casa, R.; Castaldi, F.; Pascucci, S.; Palombo, A.; Pignatti, S. A comparison of sensor resolution and calibration strategies for soil texture estimation from hyperspectral remote sensing. Geoderma
**2013**, 197, 17–26. [Google Scholar] [CrossRef] - Taghdis, S.; Farpoor, M.H.; Mahmoodabadi, M. Pedological assessments along an arid and semi-arid transect using soil spectral behavior analysis. Catena
**2022**, 214, 106288. [Google Scholar] [CrossRef] - Radočaj, D.; Jurišić, M.; Gašparović, M. The role of remote sensing data and methods in a modern approach to fertilization in precision agriculture. Remote Sens.
**2022**, 14, 778. [Google Scholar] [CrossRef] - Kalambukattu, J.G.; Kumar, S.; Arya Raj, R. Digital soil mapping in a Himalayan watershed using remote sensing and terrain parameters employing artificial neural network model. Environ. Earth Sci.
**2018**, 77, 203. [Google Scholar] [CrossRef] - Fang, Y.; Xu, L.; Wong, A.; Clausi, D.A. Multi-temporal landsat-8 images for retrieval and broad scale mapping of soil copper concentration using empirical models. Remote Sens.
**2022**, 14, 2311. [Google Scholar] [CrossRef] - Duan, M.; Guo, Z.; Zhang, X.; Wang, C. Influences of different environmental covariates on county-scale soil type identification using remote sensing images. Ecol. Indic.
**2022**, 139, 108951. [Google Scholar] [CrossRef] - Neinavaz, E.; Darvishzadeh, R.; Skidmore, A.K.; Abdullah, H. Integration of Landsat-8 thermal and visible-short wave infrared data for improving prediction accuracy of forest leaf area index. Remote Sens.
**2019**, 11, 390. [Google Scholar] [CrossRef] - Kavitha, M.; Gayathri, R.; Polat, K.; Alhudhaif, A.; Alenezi, F. Performance evaluation of deep e-CNN with integrated spatial-spectral features in hyperspectral image classification. Measurement
**2022**, 191, 110760. [Google Scholar] [CrossRef] - Yang, S.; Gu, L.; Li, X.; Jiang, T.; Ren, R. Crop classification method based on optimal feature selection and hybrid CNN-RF networks for multi-temporal remote sensing imagery. Remote Sens.
**2020**, 12, 3119. [Google Scholar] [CrossRef] - Natras, R.; Soja, B.; Schmidt, M. Ensemble Machine Learning of Random Forest, AdaBoost and XGBoost for Vertical Total Electron Content Forecasting. Remote Sens.
**2022**, 14, 3547. [Google Scholar] [CrossRef] - Li, S.; Han, Y.; Yao, X.; Yingchen, S.; Wang, J.; Zhao, Q. Electricity theft detection in power grids with deep learning and random forests. J. Electr. Comput. Eng.
**2019**, 2019, 4136874. [Google Scholar] [CrossRef] - Knauer, U.; von Rekowski, C.S.; Stecklina, M.; Krokotsch, T.; Pham Minh, T.; Hauffe, V.; Kilias, D.; Ehrhardt, I.; Sagischewski, H.; Chmara, S. Tree species classification based on hybrid ensembles of a convolutional neural network (CNN) and random forest classifiers. Remote Sens.
**2019**, 11, 2788. [Google Scholar] [CrossRef] - Li, Y.; Wang, W.; Wang, G.; Tan, Q. Actual evapotranspiration estimation over the Tuojiang River Basin based on a hybrid CNN-RF model. J. Hydrol.
**2022**, 610, 127788. [Google Scholar] [CrossRef]

**Figure 8.**Feature importance based on the RF algorithm for soil texture: (

**a**) clay, (

**c**) sand, and (

**e**) silt; and the portion of each environmental category in the input data: (

**b**) clay, (

**d**) sand, and (

**f**) silt.

**Figure 9.**Box plots for comparison of the hybrid CNN-RF, RF, and CNN models for soil properties: (

**a**) clay, (

**b**) sand, (

**c**) silt.

Soil Texture | Clay (%) | Silt (%) | Sand (%) |
---|---|---|---|

Minimum | 0 | 0 | 0 |

Maximum | 44 | 80 | 58 |

Mean | 22.322 | 64.457 | 12.867 |

Standard deviation | 6.920 | 9.249 | 9.115 |

Soil Texture | Clay (%) | Silt (%) | Sand (%) |
---|---|---|---|

Minimum | 12 | 50 | 4 |

Maximum | 36 | 76 | 26 |

Mean | 22.182 | 65.74 | 11.056 |

Standard deviation | 4.199 | 4.567 | 3.705 |

Soil Texture | Effective Parameters | Number of Parameters |
---|---|---|

Clay | NDVI, Elevation, B7, B5, B1, B2, B3, B4, MRRTF, MRVBF, Rainfall, SI, CI, LST, Temp, Aspect, RI, TWI | 18 |

Silt | NDVI, Elevation, B7, B5, B3, B4, MRRTF, MRVBF, SI, BI, CLI, CI, Slope, EVI, DR, Aspect, RI, TWI | 18 |

Sand | NDVI, Elevation, B7, B5, B1, B2, B3, B4, Rainfall, SI, BI, CLI, MRRTF, MRVBF, CI, Slope, LST, DR | 18 |

Covariate Name | Definition | Reference |
---|---|---|

Coastal aerosol (B1) | 0.43–0.45 µm | [41] |

Blue (B2) | 0.45–0.51 µm | |

Green (B3) | 0.53–0.59 µm | |

Red (B4) | 0.64–0.67 µm | |

Near-infrared (B5) | 0.85–0.88 µm | |

Short-wave infrared-2 (B7) | 2.11–2.29 µm | |

Brightness Index (BI) | ${\left(\mathrm{B}{3}^{2}+\mathrm{B}{4}^{2}\right)}^{0.5}$ | [42,43] |

Clay Index (CLI) | $\mathrm{B}6/\mathrm{B}7$ | [22] |

Coloration Index (CI) | $\left(\mathrm{B}4-\mathrm{B}3\right)/\left(\mathrm{B}4+\mathrm{B}3\right)$ | [42,44] |

Enhanced Vegetation Index (EVI) | $2.5\times \left(\frac{\mathrm{B}5-\mathrm{B}4}{\mathrm{B}5+\left(6\times \mathrm{B}4\right)-\left(7.5\times \mathrm{B}2\right)+1}\right)$ | [45] |

Land Surface Temperature (LST) | ||

Normalized Difference Vegetation Index (NDVI) | $\left(\mathrm{B}5-\mathrm{B}4\right)/\left(\mathrm{B}5+\mathrm{B}4\right)$ | [46] |

Redness Index (RI) | $\left(\mathrm{B}{4}^{2}\right)/\left(\mathrm{B}2\times \left(\mathrm{B}{3}^{3}\right)\right)$ | [44] |

Saturation Index (SI) | $\left(\mathrm{B}4-\mathrm{B}2\right)/\left(\mathrm{B}4+\mathrm{B}2\right)$ | [47] |

**Table 5.**The optimized hyperparameters and layers for each model. “✓” signifies the inclusion of specific layers in the model.

Filter/Number of Trees | Filter Size | Activation Function | CNN | RF | CNN-RF | |||
---|---|---|---|---|---|---|---|---|

Layers | L1 | Convolutional | 32 | 3 | ReLU | ✓ | - | ✓ |

L2 | Flatten | - | - | - | ✓ | - | ✓ | |

L3 | Fully connected | 64 | 2 | ReLU | ✓ | - | ✓ | |

L4 | Fully connected | 1 | - | - | ✓ | - | ✓ | |

L5 | RF | 100 | - | - | - | ✓ | ✓ | |

Other parameters | Batch_size | - | - | - | 10 | - | 10 | |

Epochs | - | - | - | 20 | - | 20 | ||

Optimizer | - | - | - | Adam | - | Adam | ||

Loss | - | - | - | MSE | - | MSE | ||

min_samples_split | - | - | - | - | 2 | 2 | ||

max_features | - | - | - | - | ‘auto’ | ‘auto’ | ||

max_depth | - | - | - | - | ‘None’ | ‘None’ | ||

bootstrap | - | - | - | - | ‘True’ | ‘True’ |

Properties | Models | Train | Test | Runtime (s) | ||||
---|---|---|---|---|---|---|---|---|

MSE (%^{2}) | RMSE (%) | ${\mathit{R}}^{2}$ | MSE (%^{2}) | RMSE (%) | ${\mathit{R}}^{2}$ | |||

Clay | CNN | 0.00016 | 0.013 | 0.981 | 0.00038 | 0.019 | 0.966 | 2.67 |

RF | 0.00079 | 0.028 | 0.910 | 0.00407 | 0.064 | 0.636 | 0.23 | |

CNN-RF | 0.00005 | 0.007 | 0.995 | 0.00010 | 0.010 | 0.982 | 0.21 | |

Sand | CNN | 0.00029 | 0.017 | 0.928 | 0.00046 | 0.022 | 0.908 | 1.36 |

RF | 0.00034 | 0.018 | 0.917 | 0.00135 | 0.037 | 0.683 | 0.44 | |

CNN-RF | 0.00003 | 0.006 | 0.992 | 0.00007 | 0.008 | 0.976 | 0.29 | |

Silt | CNN | 0.00024 | 0.016 | 0.920 | 0.00040 | 0.020 | 0.913 | 2.73 |

RF | 0.00022 | 0.015 | 0.935 | 0.00060 | 0.024 | 0.676 | 0.196 | |

CNN-RF | 0.00004 | 0.006 | 0.987 | 0.00009 | 0.010 | 0.980 | 0.215 |

Properties | Models | MSE (%) |
---|---|---|

Clay | CNN | 0.076 |

RF | 0.0679 | |

CNN-RF | 0.1027 | |

Sand | CNN | 0.095 |

RF | 0.094 | |

CNN-RF | 0.078 | |

Silt | CNN | 0.178 |

RF | 0.137 | |

CNN-RF | 0.569 |

Agricultural Areas | Forest Land | ||||||||
---|---|---|---|---|---|---|---|---|---|

Properties | Models | Min | Max | Mean | Std | Min | Max | Mean | Std |

Clay | CNN | 0.00 | 47.24 | 32.13 | 2.73 | 0.00 | 41.72 | 31.61 | 2.00 |

RF | 0.00 | 30.06 | 25.52 | 1.42 | 0.00 | 29.02 | 23.10 | 1.04 | |

CNN-RF | 0.00 | 33.80 | 30.99 | 2.19 | 0.00 | 33.80 | 30.77 | 1.69 | |

Sand | CNN | 3.3 | 28.7 | 27.6 | 2.4 | 3.20 | 28.70 | 25.50 | 3.33 |

RF | 0.00 | 17.47 | 11.70 | 0.46 | 0.00 | 18.30 | 10.64 | 0.80 | |

CNN-RF | 0.00 | 22.93 | 5.07 | 1.32 | 0.00 | 23.41 | 4.15 | 0.47 | |

Silt | CNN | 0.00 | 72.21 | 49.26 | 3.71 | 0.00 | 78.80 | 64.72 | 4.31 |

RF | 0.00 | 67.96 | 63.04 | 1.45 | 0.00 | 68.23 | 63.63 | 2.59 | |

CNN-RF | 0.00 | 72.71 | 52.86 | 2.09 | 0.00 | 74.73 | 65.01 | 4.32 |

**Table 9.**The statistical parameters of the modeled soil texture on residential areas and uncovered plains.

Residential Areas | Uncovered Plains | ||||||||
---|---|---|---|---|---|---|---|---|---|

Properties | Models | Min | Max | Mean | Std | Min | Max | Mean | Std |

Clay | CNN | 0.00 | 40.11 | 32.51 | 2.37 | 0.00 | 43.90 | 30.64 | 3.18 |

RF | 0.00 | 29.92 | 26.87 | 1.26 | 0.00 | 29.75 | 25.01 | 1.46 | |

CNN-RF | 0.00 | 33.80 | 31.37 | 1.92 | 0.00 | 33.80 | 29.78 | 2.68 | |

Sand | CNN | 3.34 | 28.70 | 26.27 | 2.77 | 3.20 | 28.70 | 24.21 | 2.97 |

RF | 0.00 | 15.77 | 11.68 | 0.36 | 0.00 | 16.72 | 11.65 | 0.57 | |

CNN-RF | 0.00 | 21.26 | 4.47 | 0.83 | 0.00 | 21.25 | 4.88 | 1.11 | |

Silt | CNN | 0.00 | 69.74 | 47.45 | 2.81 | 0.00 | 74.17 | 49.61 | 5.07 |

RF | 0.00 | 66.81 | 62.82 | 0.84 | 0.00 | 67.77 | 63.53 | 1.45 | |

CNN-RF | 0.00 | 69.78 | 52.41 | 1.05 | 0.00 | 72.68 | 53.36 | 2.62 |

Water Bodies | Range Land | ||||||||
---|---|---|---|---|---|---|---|---|---|

Properties | Models | Min | Max | Mean | Std | Min | Max | Mean | Std |

Clay | CNN | 0.00 | 40.70 | 32.67 | 2.47 | 0.00 | 42.78 | 30.04 | 2.92 |

RF | 0.00 | 29.91 | 26.18 | 1.32 | 0.00 | 30.02 | 24.04 | 1.62 | |

CNN-RF | 0.00 | 33.80 | 31.40 | 1.95 | 0.00 | 33.80 | 29.31 | 2.45 | |

Sand | CNN | 5.50 | 28.70 | 28.06 | 1.48 | 3.20 | 24.34 | 22.34 | 4.77 |

RF | 0.00 | 13.40 | 11.68 | 0.37 | 0.00 | 18.21 | 11.03 | 0.99 | |

CNN-RF | 0.00 | 11.84 | 5.76 | 1.82 | 0.00 | 23.33 | 4.44 | 0.88 | |

Silt | CNN | 0.00 | 63.94 | 48.44 | 3.00 | 0.00 | 77.30 | 55.87 | 6.64 |

RF | 0.00 | 66.94 | 62.79 | 1.23 | 0.00 | 68.41 | 64.23 | 1.92 | |

CNN-RF | 0.00 | 63.94 | 52.43 | 1.29 | 0.00 | 75.00 | 57.33 | 5.02 |

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |

© 2023 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**

Hosseini, F.S.; Seo, M.B.; Razavi-Termeh, S.V.; Sadeghi-Niaraki, A.; Jamshidi, M.; Choi, S.-M.
Geospatial Artificial Intelligence (GeoAI) and Satellite Imagery Fusion for Soil Physical Property Predicting. *Sustainability* **2023**, *15*, 14125.
https://doi.org/10.3390/su151914125

**AMA Style**

Hosseini FS, Seo MB, Razavi-Termeh SV, Sadeghi-Niaraki A, Jamshidi M, Choi S-M.
Geospatial Artificial Intelligence (GeoAI) and Satellite Imagery Fusion for Soil Physical Property Predicting. *Sustainability*. 2023; 15(19):14125.
https://doi.org/10.3390/su151914125

**Chicago/Turabian Style**

Hosseini, Fatemeh Sadat, Myoung Bae Seo, Seyed Vahid Razavi-Termeh, Abolghasem Sadeghi-Niaraki, Mohammad Jamshidi, and Soo-Mi Choi.
2023. "Geospatial Artificial Intelligence (GeoAI) and Satellite Imagery Fusion for Soil Physical Property Predicting" *Sustainability* 15, no. 19: 14125.
https://doi.org/10.3390/su151914125