Nondestructive investigation of soil moisture level using optical system
Soils are one of the essential resources consisting of unconsolidated mineral or organic material on the surface of the Earth; it plays an important role in the growth of land plants. Soil testing is an effort to assess the soil constituents and moisture level; this information is useful to evaluate...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English English English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/986/1/24p%20MARS%20WAI%20HONG%20XUAN.pdf http://eprints.uthm.edu.my/986/2/MARS%20WAI%20HONG%20XUAN%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/986/3/MARS%20WAI%20HONG%20XUAN%20WATERMARK.pdf http://eprints.uthm.edu.my/986/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Soils are one of the essential resources consisting of unconsolidated mineral or organic material on the surface of the Earth; it plays an important role in the growth of land plants. Soil testing is an effort to assess the soil constituents and moisture level; this information is useful to evaluate soil fertility and plant survival. This research describes the use of an optical system combined with Artificial Neural Network (ANN) for wireless and nondestructive prediction of soil moisture level. The former system comprising of Near Infrared (NIR) emitters of wavelengths 1200 nm and 1450 nm, and a photodetector mounted on a mobile platform for remote and automated soil moisture measurement in loams and peats holding different amount of water. There were 63 and 90 sets of data from loams and peats, respectively, used in the development of the dual-stage multiclass ANN model, wherein measurement of light attenuation (from nondestructive system) was correlated with percent soil moisture (from destructive gold standard approach). Since there is a considerable overlap in the value of the measurables (for both soil types), this work employed ANN model for each of the considered soil. The result revealed a relatively good performance in the training of the NN with regression, R of 0.8817 and 0.8881, and satisfactory error performance of 0.7898 and 1.172, for loams and peats, respectively. The testing of the system on 50 new samples of loam and peat showed a considerably high mean accuracy of 92 % for loams while 82 % was observed for peats. This study attributes the poorer performance of the system on peats to the analog to digital conversion resolution of HL-69 sensor (measurement of percent soil moisture), and structure and properties of the corresponding soil. This work concluded that the developed technology may be feasible for use in the future design and improvement of agricultural soil management. |
|---|