A simple approach to estimate coastal soil salinity using digital camera images
Lu Xu
A E , Raphael A. Viscarra Rossel B , Juhwan Lee B C , Zhichun Wang D and Hongyuan Ma D
+ Author Affiliations
- Author Affiliations
A School of Geography, Geomatics, and Planning, Jiangsu Normal University, Xuzhou 221116, China.
B School of Molecular and Life Sciences, Faculty of Science and Engineering, Curtin University, Perth, Western Australia, Australia.
C Department of Agronomy and Medicinal Plant Resources, College of Life Sciences, Gyeongnam National University of Science and Technology, Jinju, South Korea.
D Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, 4888 Shengbei Street, Changchun 130012, China.
E Corresponding author. Email: luxa1023@jsnu.edu.cn
Soil Research 58(8) 737-747 https://doi.org/10.1071/SR20009
Submitted: 8 January 2020 Accepted: 28 August 2020 Published: 1 October 2020
Abstract
Soil salinisation is a global problem that hinders the sustainable development of ecosystems and agricultural production. Remote and proximal sensing technologies have been used to effectively evaluate soil salinity over large scales, but research on digital camera images is still lacking. In this study, we propose to relate the pixel brightness of soil surface digital images to the soil salinity information. We photographed the surface of 93 soils in the field at different times and weather conditions, and sampled the corresponding soils for laboratory analyses of soil salinity information. Results showed that the pixel digital numbers were related to soil salinity, especially at the intermediate and higher brightness levels. Based on this relationship, we employed random forest (RF) and partial least-squares regression (PLSR) to model soil salt content and ion concentrations, and applied root mean squared error, coefficient of determination and Lin’s concordance correlation coefficient to evaluate the accuracy of models. We found that ions with high concentration were estimated more accurately than ions with low concentrations, and RF models performed overall better than PLSR models. However, the method is only suitable for bare land of coastal soil, and verification is needed for other conditions. In conclusion, a new approach of using digital camera images has good potential to predict and manage soil salinity in the context of precision agriculture with the rapid development of unmanned aerial vehicles.
Keywords: coastal soil salinity, colour component, digital camera, random forest.
References
Adamchuk VI, Rossel RAV (2011) Precision agriculture: proximal soil sensing. In ‘Encyclopedia of Agrophysics. Encyclopedia of Earth Sciences Series’. (Eds J Gliński, J Horabik, J Lipiec) (Springer, Dordrecht). https://doi.org/10.1007/978-90-481-3585-1_126Aitkenhead M, Donnelly D, Coull M, Gwatkin R (2016) Estimating soil properties with a mobile phone. In ‘Digital Soil Morphometrics’. (Eds AE Hartemink, B Minasny) pp. 89–110. (Springer International Publishing: Cham)
Allbed A, Kumar L (2013) Soil salinity mapping and monitoring in arid and semi-arid regions using remote sensing technology: a review. Advances in Remote Sensing 02, 373–385.
| Soil salinity mapping and monitoring in arid and semi-arid regions using remote sensing technology: a review.Crossref | GoogleScholarGoogle Scholar |
Bao K, Shen J, Sapkota A (2017) High-resolution enrichment of trace metals in a west coastal wetland of the southern Yellow Sea over the last 150 years. Journal of Geochemical Exploration 176, 136–145.
| High-resolution enrichment of trace metals in a west coastal wetland of the southern Yellow Sea over the last 150 years.Crossref | GoogleScholarGoogle Scholar |
Breiman L (2001) Random forests. Machine Learning 45, 5–32.
| Random forests.Crossref | GoogleScholarGoogle Scholar |
Candiago S, Remondino F, De Giglio M, Dubbini M, Gattelli M (2015) Evaluating multispectral images and vegetation indices for precision farming applications from UAV images. Remote Sensing 7, 4026–4047.
| Evaluating multispectral images and vegetation indices for precision farming applications from UAV images.Crossref | GoogleScholarGoogle Scholar |
Choodum A, Kanatharana P, Wongniramaikul W, Nic Daeid N (2013) Using the iPhone as a device for a rapid quantitative analysis of trinitrotoluene in soil. Talanta 115, 143–149.
| Using the iPhone as a device for a rapid quantitative analysis of trinitrotoluene in soil.Crossref | GoogleScholarGoogle Scholar | 24054571PubMed |
Cutler DR, Edwards TC, Beard KH, Cutler A, Hess KT, Gibson J, Lawler JJ (2007) rRandom forests for classification in ecology. Ecology 88, 2783–2792.
| rRandom forests for classification in ecology.Crossref | GoogleScholarGoogle Scholar | 18051647PubMed |
de Oliveira Morais PA, de Souza DM, Madari BE, Soares AdS, de Oliveira AE (2019) Using image analysis to estimate the soil organic carbon content. Microchemical Journal 147, 775–781.
| Using image analysis to estimate the soil organic carbon content.Crossref | GoogleScholarGoogle Scholar |
Deng L, Mao Z, Li X, Hu Z, Duan F, Yan Y (2018) UAV-based multispectral remote sensing for precision agriculture: a comparison between different cameras. ISPRS Journal of Photogrammetry and Remote Sensing 146, 124–136.
| UAV-based multispectral remote sensing for precision agriculture: a comparison between different cameras.Crossref | GoogleScholarGoogle Scholar |
Farifteh J, Tolpekin V, Van Der Meer F, Sukchan S (2010) Salinity modelling by inverted Gaussian parameters of soil reflectance spectra. International Journal of Remote Sensing 31, 3195–3210.
| Salinity modelling by inverted Gaussian parameters of soil reflectance spectra.Crossref | GoogleScholarGoogle Scholar |
Fei YH, She DL, Yao ZD, Li L, Ding JH, Hu W (2017) Hierarchical Bayesian models for predicting soil salinity and sodicity characteristics in a coastal reclamation region. Ecological Engineering 104, 45–56.
| Hierarchical Bayesian models for predicting soil salinity and sodicity characteristics in a coastal reclamation region.Crossref | GoogleScholarGoogle Scholar |
Feng QL, Liu JT, Gong JH (2015) UAV remote sensing for urban vegetation mapping using random forest and texture analysis. Remote Sensing 7, 1074–1094.
| UAV remote sensing for urban vegetation mapping using random forest and texture analysis.Crossref | GoogleScholarGoogle Scholar |
Gao J, Bai F, Yang Y, Gao S, Liu Z, Li J (2012) Influence of spartina colonization on the supply and accumulation of organic carbon in tidal salt marshes of Northern Jiangsu Province, China. Journal of Coastal Research 28, 486–498.
| Influence of spartina colonization on the supply and accumulation of organic carbon in tidal salt marshes of Northern Jiangsu Province, China.Crossref | GoogleScholarGoogle Scholar |
Hardin PJ, Jensen RR (2011) Small-scale unmanned aerial vehicles in environmental remote sensing: challenges and opportunities. GIScience & Remote Sensing 48, 99–111.
| Small-scale unmanned aerial vehicles in environmental remote sensing: challenges and opportunities.Crossref | GoogleScholarGoogle Scholar |
Hendrik W, Titia M, Michael ES, Armin K, Philip J (2014) ‘Remote Sensing of Soils.’ (University of Zurich: Switzerland)
Hu J, Peng J, Zhou Y, Xu D, Zhao R, Jiang Q, Fu T, Wang F, Shi Z (2019) Quantitative estimation of soil salinity using UAV-borne hyperspectral and satellite multispectral images. Remote Sensing 11, 736
| Quantitative estimation of soil salinity using UAV-borne hyperspectral and satellite multispectral images.Crossref | GoogleScholarGoogle Scholar |
Huang J, Mokhtari AR, Cohen DR, Monteiro Santos FA, Triantafilis J (2015) Modelling soil salinity across a gilgai landscape by inversion of EM38 and EM31 data. European Journal of Soil Science 66, 951–960.
| Modelling soil salinity across a gilgai landscape by inversion of EM38 and EM31 data.Crossref | GoogleScholarGoogle Scholar |
Hunt GR (1977) Spectral signatures of particulate minerals in the visible and near infrared. Geophysics 42, 501–513.
| Spectral signatures of particulate minerals in the visible and near infrared.Crossref | GoogleScholarGoogle Scholar |
Ivushkin K, Bartholomeus H, Bregt AK, Pulatov A, Franceschini MHD, Kramer H, van Loo EN, Jaramillo Roman V, Finkers R (2019) UAV based soil salinity assessment of cropland. Geoderma 338, 502–512.
| UAV based soil salinity assessment of cropland.Crossref | GoogleScholarGoogle Scholar |
Jackson, MLR (2005) ‘Soil Chemical Analysis: Advanced Course.’ (Parallel Press: University of Wisconsin-Madison Libraries)
Jung A, Vohland M, Thiele-Bruhn S (2015) Use of a portable camera for proximal soil sensing with hyperspectral image data. Remote Sensing 7, 11434–11448.
| Use of a portable camera for proximal soil sensing with hyperspectral image data.Crossref | GoogleScholarGoogle Scholar |
Kursa MB, Rudnicki WR (2010) Feature selection with the Boruta package. Journal of Statistical Software 36, 13
| Feature selection with the Boruta package.Crossref | GoogleScholarGoogle Scholar |
Levin N, Ben-Dor E, Singer A (2005) A digital camera as a tool to measure colour indices and related properties of sandy soils in semi-arid environments. International Journal of Remote Sensing 26, 5475–5492.
| A digital camera as a tool to measure colour indices and related properties of sandy soils in semi-arid environments.Crossref | GoogleScholarGoogle Scholar |
Li JG, Pu LJ, Zhu M, Dai XQ, Xu Y, Chen XJ, Zhang LF, Zhang RS (2015) Monitoring soil salt content using HJ-1A hyperspectral data: a case study of coastal areas in Rudong County, Eastern China. Chinese Geographical Science 25, 213–223.
| Monitoring soil salt content using HJ-1A hyperspectral data: a case study of coastal areas in Rudong County, Eastern China.Crossref | GoogleScholarGoogle Scholar |
Lin L (1989) A concordance correlation-coefficient to evaluate reproducibility. Biometrics 45, 255–268.
| A concordance correlation-coefficient to evaluate reproducibility.Crossref | GoogleScholarGoogle Scholar | 2720055PubMed |
Maes WH, Steppe K (2019) Perspectives for remote sensing with unmanned aerial vehicles in precision agriculture. Trends in Plant Science 24, 152–164.
| Perspectives for remote sensing with unmanned aerial vehicles in precision agriculture.Crossref | GoogleScholarGoogle Scholar | 30558964PubMed |
Metternicht GI, Zinck JA (2003) Remote sensing of soil salinity: potentials and constraints. Remote Sensing of Environment 85, 1–20.
| Remote sensing of soil salinity: potentials and constraints.Crossref | GoogleScholarGoogle Scholar |
Metternicht G, Zinck A (2008) ‘Remote Sensing of Soil Salinization: Impact on Land Management.’ (CRC Press: Boca Raton)
Peng J, Ji WJ, Ma ZQ, Li S, Chen SC, Zhou LQ, Shi Z (2016) Predicting total dissolved salts and soluble ion concentrations in agricultural soils using portable visible near-infrared and mid-infrared spectrometers. Biosystems Engineering 152, 94–103.
| Predicting total dissolved salts and soluble ion concentrations in agricultural soils using portable visible near-infrared and mid-infrared spectrometers.Crossref | GoogleScholarGoogle Scholar |
Persson M (2005) Estimating surface soil moisture from soil color using image analysis. Vadose Zone Journal 4, 1119–1122.
| Estimating surface soil moisture from soil color using image analysis.Crossref | GoogleScholarGoogle Scholar |
Qadir M, Schubert S, Ghafoor A, Murtaza G (2001) Amelioration strategies for sodic soils: a review. Land Degradation & Development 12, 357–386.
| Amelioration strategies for sodic soils: a review.Crossref | GoogleScholarGoogle Scholar |
R Development Core Team (2017) ‘R: A Language and Environment for Statistical Computing.’ (R Foundation for Statistical Computing: Vienna, Austria)
Regnier P, Friedlingstein P, Ciais P, Mackenzie FT, Gruber N, Janssens IA, Laruelle GG, Lauerwald R, Luyssaert S, Andersson AJ, Arndt S, Arnosti C, Borges AV, Dale AW, Gallego-Sala A, Goddéris Y, Goossens N, Hartmann J, Heinze C, Ilyina T, Joos F, LaRowe DE, Leifeld J, Meysman FJR, Munhoven G, Raymond PA, Spahni R, Suntharalingam P, Thullner M (2013) Anthropogenic perturbation of the carbon fluxes from land to ocean. Nature Geoscience 6, 597
| Anthropogenic perturbation of the carbon fluxes from land to ocean.Crossref | GoogleScholarGoogle Scholar |
Ren J, Li X, Zhao K, Fu B, Jiang T (2016) Study of an on-line measurement method for the salt parameters of soda-saline soils based on the texture features of cracks. Geoderma 263, 60–69.
| Study of an on-line measurement method for the salt parameters of soda-saline soils based on the texture features of cracks.Crossref | GoogleScholarGoogle Scholar |
Rhoades JD, Ingvalson RD (1971) Determining salinity in field soils with soil resistance measurements. Soil Science Society of America Journal 35, 54–60.
| Determining salinity in field soils with soil resistance measurements.Crossref | GoogleScholarGoogle Scholar |
Rodriguez-Moreno F, Kren J, Zemek F, Novak J, Lukas V, Pikl M (2017) Advantage of multispectral imaging with sub-centimeter resolution in precision agriculture: generalization of training for supervised classification. Precision Agriculture 18, 615–634.
| Advantage of multispectral imaging with sub-centimeter resolution in precision agriculture: generalization of training for supervised classification.Crossref | GoogleScholarGoogle Scholar |
Strobl C, Boulesteix A-L, Kneib T, Augustin T, Zeileis A (2008) Conditional variable importance for random forests. BMC Bioinformatics 9, 307
| Conditional variable importance for random forests.Crossref | GoogleScholarGoogle Scholar | 18620558PubMed |
Viscarra Rossel RA, Mcbratney AB (1998) Soil chemical analytical accuracy and costs: implications from precision agriculture. Australian Journal of Experimental Agriculture 38, 765–775.
| Soil chemical analytical accuracy and costs: implications from precision agriculture.Crossref | GoogleScholarGoogle Scholar |
Viscarra Rossel RA, Walvoort DJJ, McBratney AB, Janik LJ, Skjemstad JO (2006) Visible, near infrared, mid infrared or combined diffuse reflectance spectroscopy for simultaneous assessment of various soil properties. Geoderma 131, 59–75.
| Visible, near infrared, mid infrared or combined diffuse reflectance spectroscopy for simultaneous assessment of various soil properties.Crossref | GoogleScholarGoogle Scholar |
Viscarra Rossel RA, Fouad Y, Walter C (2008) Using a digital camera to measure soil organic carbon and iron contents. Biosystems Engineering 100, 149–159.
| Using a digital camera to measure soil organic carbon and iron contents.Crossref | GoogleScholarGoogle Scholar |
Viscarra Rossel RA, Mcbratney AB, Minasny B (2010) ‘Proximal Soil Sensing.’ (Springer Netherlands)
Viscarra Rossel RA, Webster R, Kidd D (2014) Mapping gamma radiation and its uncertainty from weathering products in a Tasmanian landscape with a proximal sensor and random forest kriging. Earth Surface Processes and Landforms 39, 735–748.
| Mapping gamma radiation and its uncertainty from weathering products in a Tasmanian landscape with a proximal sensor and random forest kriging.Crossref | GoogleScholarGoogle Scholar |
Werner AD, Bakker M, Post VEA, Vandenbohede A, Lu C, Ataie-Ashtiani B, Simmons CT, Barry DA (2013) Seawater intrusion processes, investigation and management: recent advances and future challenges. Advances in Water Resources 51, 3–26.
| Seawater intrusion processes, investigation and management: recent advances and future challenges.Crossref | GoogleScholarGoogle Scholar |
Wilson WJ, Yueh SH, Dinardo SJ, Chazanoff SL, Kitiyakara A, Li FK, Rahmat-Samii Y (2001) Passive active L- and S-band (PALS) microwave sensor for ocean salinity and soil moisture measurements. IEEE Transactions on Geoscience and Remote Sensing 39, 1039–1048.
| Passive active L- and S-band (PALS) microwave sensor for ocean salinity and soil moisture measurements.Crossref | GoogleScholarGoogle Scholar |
Wu CW, Xia JX, Yang H, Yang Y, Zhang YC, Cheng FW (2018) Rapid determination of soil organic matter content based on soil colour obtained by a digital camera. International Journal of Remote Sensing 39, 6557–6571.
| Rapid determination of soil organic matter content based on soil colour obtained by a digital camera.Crossref | GoogleScholarGoogle Scholar |
Xu C, Zeng W, Huang J, Wu J, Van Leeuwen WJD (2016) Prediction of soil moisture content and soil salt concentration from hyperspectral laboratory and field data. Remote Sensing 8, 42
| Prediction of soil moisture content and soil salt concentration from hyperspectral laboratory and field data.Crossref | GoogleScholarGoogle Scholar |
Xu L, Wang Z, Nyongesah JM (2019a) Soil column sample height influences soil spectral reflectance in laboratory experiment. Photonirvachak (Dehra Dun) 47, 1187–1196.
| Soil column sample height influences soil spectral reflectance in laboratory experiment.Crossref | GoogleScholarGoogle Scholar |
Xu L, Zheng C, Wang Z, Nyongesah MJ (2019b) A digital camera as an alternative tool for estimating soil salinity and soil surface roughness. Geoderma 341, 68–75.
| A digital camera as an alternative tool for estimating soil salinity and soil surface roughness.Crossref | GoogleScholarGoogle Scholar |
Yang R, Guo W (2019) Using Sentinel-1 imagery for soil salinity prediction under the condition of coastal restoration. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 12, 1482–1488.
| Using Sentinel-1 imagery for soil salinity prediction under the condition of coastal restoration.Crossref | GoogleScholarGoogle Scholar |
Yang R-M, Zhang G-L, Liu F, Lu Y-Y, Yang F, Yang F, Yang M, Zhao Y-G, Li D-C (2016) Comparison of boosted regression tree and random forest models for mapping topsoil organic carbon concentration in an alpine ecosystem. Ecological Indicators 60, 870–878.
| Comparison of boosted regression tree and random forest models for mapping topsoil organic carbon concentration in an alpine ecosystem.Crossref | GoogleScholarGoogle Scholar |
Yao RJ, Yang JS, Zhang TJ, Hong LZ, Wang MW, Yu SP, Wang XP (2014) Studies on soil water and salt balances and scenarios simulation using SaltMod in a coastal reclaimed farming area of eastern China. Agricultural Water Management 131, 115–123.
| Studies on soil water and salt balances and scenarios simulation using SaltMod in a coastal reclaimed farming area of eastern China.Crossref | GoogleScholarGoogle Scholar |
Yin AJ, Zhang M, Gao C, Yang XH, Xu Y, Wu PB, Zhang H (2016) Salinity evolution of coastal soils following reclamation and intensive usage, Eastern China. Environmental Earth Sciences 75, 1281
| Salinity evolution of coastal soils following reclamation and intensive usage, Eastern China.Crossref | GoogleScholarGoogle Scholar |
Zhang C, Kovacs JM (2012) The application of small unmanned aerial systems for precision agriculture: a review. Precision Agriculture 13, 693–712.
| The application of small unmanned aerial systems for precision agriculture: a review.Crossref | GoogleScholarGoogle Scholar |
Zhang Y, Hartemink AE (2019) A method for automated soil horizon delineation using digital images. Geoderma 343, 97–115.
| A method for automated soil horizon delineation using digital images.Crossref | GoogleScholarGoogle Scholar |
Zhang T-T, Zeng S-L, Gao Y, Ouyang Z-T, Li B, Fang C-M, Zhao B (2011) Using hyperspectral vegetation indices as a proxy to monitor soil salinity. Ecological Indicators 11, 1552–1562.
| Using hyperspectral vegetation indices as a proxy to monitor soil salinity.Crossref | GoogleScholarGoogle Scholar |
