Scientists developed a novel method of automatic soil mapping

February 15, 2021

A team of soil scientists developed a new approach to the automatic generation and updating of soil maps. Having applied machine learning technologies to a set of rules traditionally used by experts in manual mapping, the team obtained a highly accurate model that provides easy-to-interpret results. The study was published in ISPRS International Journal of Geo-Information.

Many software solutions for digital soil mapping are based on statistical models. The accuracy of such programs is limited because statistical models depend on the quality and quantity of field data and can ignore local irregularities in soil properties. It is difficult to obtain accurate and useful information from such maps because they are built based on extremely complex, sometimes even seemingly illogical models. To make digital mapping models clearer, more manageable, and accurate, one could formalize traditional soil mapping rules and add them to the existing software. A team of scientists from RUDN University together with their colleagues from the Dokuchyaev Soil Science Institute suggested a new approach to using expert knowledge of soil mapping in digital solutions.

"Many digital tools for soil mapping contain certain elements of qualitative analysis. However, the accuracy of the maps could be increased by means of imitating the traditional work process of a soil mapping expert in a software solution," said Prof. Igor Savin, an Academician of the Russian Academy of Sciences and Doctor Agricultural Sciences from the Department of System Ecology, RUDN University.

The new method can be used to develop regional soil maps. It is based on machine learning techniques, namely, the building of the so-called decision trees. The values that a decision tree is based on are key soil formation factors that are usually taken into consideration during manual mapping. The data on which the model was trained was collected from different sources: for example, information about plants was taken from satellite images and a lot of quantitative data came from topographic maps. As for the qualitative data (the rules used to identify types of soil), the model extracted it from obsolete soil maps during training. Experts in decision trees also made some changes to the input data which were considered another source of information by the system.

The new approach was tested on a 1,560 sq.m area in Belgorod Region, Russia. It is a flat terrain with a large share of black soils mainly used in agriculture. The new model turned out to be more compact than traditional digital soil mapping methods: it used 20-29 variables instead of 142-162. This made the model and the maps generated on its basis easier to interpret. After expert manual adjustment of the decision tree, the accuracy of the maps reached 76%.

"The accuracy of map generation can be further increased, but it requires meticulous fine-tuning of the models. At this stage, we intended to confirm our main principle: classical soil formation factors could be used in digital mapping instead of indexes that are often difficult to understand. Our method can produce mapping models that would be easy to work with and to readjust depending on environmental changes," added Prof. Igor Savin from RUDN University.

RUDN University

Related Data Articles from Brightsurf:

Keep the data coming
A continuous data supply ensures data-intensive simulations can run at maximum speed.

Astronomers are bulging with data
For the first time, over 250 million stars in our galaxy's bulge have been surveyed in near-ultraviolet, optical, and near-infrared light, opening the door for astronomers to reexamine key questions about the Milky Way's formation and history.

Novel method for measuring spatial dependencies turns less data into more data
Researcher makes 'little data' act big through, the application of mathematical techniques normally used for time-series, to spatial processes.

Ups and downs in COVID-19 data may be caused by data reporting practices
As data accumulates on COVID-19 cases and deaths, researchers have observed patterns of peaks and valleys that repeat on a near-weekly basis.

Data centers use less energy than you think
Using the most detailed model to date of global data center energy use, researchers found that massive efficiency gains by data centers have kept energy use roughly flat over the past decade.

Storing data in music
Researchers at ETH Zurich have developed a technique for embedding data in music and transmitting it to a smartphone.

Life data economics: calling for new models to assess the value of human data
After the collapse of the blockchain bubble a number of research organisations are developing platforms to enable individual ownership of life data and establish the data valuation and pricing models.

Geoscience data group urges all scientific disciplines to make data open and accessible
Institutions, science funders, data repositories, publishers, researchers and scientific societies from all scientific disciplines must work together to ensure all scientific data are easy to find, access and use, according to a new commentary in Nature by members of the Enabling FAIR Data Steering Committee.

Democratizing data science
MIT researchers are hoping to advance the democratization of data science with a new tool for nonstatisticians that automatically generates models for analyzing raw data.

Getting the most out of atmospheric data analysis
An international team including researchers from Kanazawa University used a new approach to analyze an atmospheric data set spanning 18 years for the investigation of new-particle formation.

Read More: Data News and Data Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to