Automated Measurement of the Water Drop Penetration Time for the Analysis of Soil Water Repellency

In this work, we develop an innovative system for the automated measurement of Water Drop Penetration Time (WDPT) - a parameter that is conventionally used for evaluating soil water repellency (SWR). Increased SWR can be a reason for plant stress and poor crop yields, create a risk of potential water runoff and floods and thus can pose risks to life and property loss. Timely evaluation of soil conditions can save resources and win time for responding to environmental disasters. Manual measurements of WDPT are labor-intensive, subjective, tend to produce variability of outcomes, and also not always available in remote or not easily reachable locations. To overcome these limitations, and perform tests in both lab settings and field deployment, we developed a system for automatically performing a standardized WDPT test, estimating WDPT and evaluating SWR. The experimental system records video clips of the water drop placed on the soil surface from a fixed height and in a fixed small volume using a solenoid valve. The entire process from a drop landing on the soil surface to its complete absorption is modeled as a temporal action and consequently, the WDPT estimation is solved using Temporal Action Localisation (TAL) deep learning models. A number of decisions are made for identifying the most efficient models, and designing the end-to-end processing system for WDPT estimation and SWR evaluation. This research contributes to the National Science Foundation (NSF) EPSCoR project “Harnessing the Data Revolution for Fire Science (HDRFS)” through the seed grant “A Machine Learning Framework for Measuring Water Drop Penetration Time (WDPT) of Fire-Affected Soils.