Soil pesticides pollution detection and specific recognition using electronic nose

Abstract

The detection of pesticides in soil has been widely studied. However, it is difficult to realize large-scale in-situ detection with current methods. In this paper, we proposed distributed soil pesticides detection and specific recognition framework and verified the feasibility of using electronic nose as the detector of membrane interface probe to detect pesticides in soil. Six brands of pesticides in three types and healthy soil were specifically identified. Furthermore, semi quantitative calculation of pesticides was realized to provide decision-making basis for staff. To minimize the computing resource and energy consumption, the data-driven method was used to determine the best sensor array in the pre design stage of the whole frame. The experiment results show that the proposed method can quickly and effectively detect soil pollution and accurately analyze various pesticides in the soil.