# Kriging-Based Robotic Exploration for Soil Moisture Mapping Using a Cosmic-Ray Sensor

arXiv: https://arxiv.org/abs/1811.05384 · HTML: https://mlsanity.com/paper/1811.05384/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2018.

## Built on by (most cited first, 3 of 3)

- [Adaptive Selection of Informative Path Planning Strategies via Reinforcement Learning](https://mlsanity.com/paper/2108.06618/) (2021)
- [Towards technological adaptation of advanced farming through AI, IoT, and Robotics: A Comprehensive overview](https://mlsanity.com/paper/2202.10459/) (2022)
- [Data Optimisation of Machine Learning Models for Smart Irrigation in Urban Parks](https://mlsanity.com/paper/2410.02335/) (2024)

## Abstract (arXiv)

Soil moisture monitoring is a fundamental process to enhance agricultural outcomes and to protect the environment. The traditional methods for measuring moisture content in soil are laborious and expensive, and therefore there is a growing interest in developing sensors and technologies which can reduce the effort and costs. In this work, we propose to use an autonomous mobile robot equipped with a state-of-the-art non-contact soil moisture sensor that builds moisture maps on the fly and automatically selects the most optimal sampling locations. The robot is guided by an autonomous exploration strategy driven by the quality of the soil moisture model which indicates areas of the field where the information is less precise. The sensor model follows the Poisson distribution and we demonstrate how to integrate such measurements into the kriging framework. We also investigate a range of different exploration strategies and assess their usefulness through a set of evaluation experiments based on real soil moisture data collected from two different fields. We demonstrate the benefits of using the adaptive measurement interval and adaptive sampling strategies for building better quality soil moisture models. The presented method is general and can be applied to other scenarios where the measured phenomena directly affects the acquisition time and needs to be spatially mapped.