TY - JOUR
T1 - Predicting soil texture from smartphone-captured digital images and an application
AU - Swetha, R. K.
AU - Bende, Prajwal
AU - Singh, Kabeer
AU - Gorthi, Srikanth
AU - Biswas, Asim
AU - Li, Bin
AU - Weindorf, David C.
AU - Chakraborty, Somsubhra
N1 - Publisher Copyright:
© 2020 Elsevier B.V.
PY - 2020/10/15
Y1 - 2020/10/15
N2 - The rapid and non-invasive prediction of soil sand, silt, and clay is becoming increasingly attractive given the laborious nature of traditional soil textural analysis. This study proposed a novel and cheap setup comprising a smartphone, a custom-made dark chamber, and a smartphone application for predicting soil texture of the dried, ground, and sieved samples. The image acquisition system was used to capture triplicate images from 90 mineral soil samples, representing a wide textural variability from sand to clay. Local features, color features, and texture features were extracted from the cropped images and subsequently used in different combinations to predict laboratory-measured clay, silt, and sand via random forest (RF) and convolutional neural network (CNN) algorithms. Results indicated high prediction accuracy for clay (R2 = 0.97–0.98) and sand (R2 = 0.96–0.98) and moderate prediction accuracy for silt (R2 = 0.62–0.75) using both algorithms. Color features outperformed all other image-extracted features and showed the maximum influence on RF model performance. The better performance of the color features can be attributed to the color features of mineral matter and soil organic matter (SOM). An Android-based smartphone application based on the calibrated CNN model was able to predict and return soil textural values. These results exhibited the potential of the proposed system as a proximal sensor for rapid, cost-effective, and eco-friendly soil textural analysis using computer-vision and deep learning. More research is warranted to augment the setup design, develop a standalone mobile application, and measure the impacts of soil moisture and high SOM on the model prediction performance to extend the approach for on-site prediction of soil texture.
AB - The rapid and non-invasive prediction of soil sand, silt, and clay is becoming increasingly attractive given the laborious nature of traditional soil textural analysis. This study proposed a novel and cheap setup comprising a smartphone, a custom-made dark chamber, and a smartphone application for predicting soil texture of the dried, ground, and sieved samples. The image acquisition system was used to capture triplicate images from 90 mineral soil samples, representing a wide textural variability from sand to clay. Local features, color features, and texture features were extracted from the cropped images and subsequently used in different combinations to predict laboratory-measured clay, silt, and sand via random forest (RF) and convolutional neural network (CNN) algorithms. Results indicated high prediction accuracy for clay (R2 = 0.97–0.98) and sand (R2 = 0.96–0.98) and moderate prediction accuracy for silt (R2 = 0.62–0.75) using both algorithms. Color features outperformed all other image-extracted features and showed the maximum influence on RF model performance. The better performance of the color features can be attributed to the color features of mineral matter and soil organic matter (SOM). An Android-based smartphone application based on the calibrated CNN model was able to predict and return soil textural values. These results exhibited the potential of the proposed system as a proximal sensor for rapid, cost-effective, and eco-friendly soil textural analysis using computer-vision and deep learning. More research is warranted to augment the setup design, develop a standalone mobile application, and measure the impacts of soil moisture and high SOM on the model prediction performance to extend the approach for on-site prediction of soil texture.
KW - Convolutional neural network
KW - Mobile application
KW - Random forest
KW - Smartphone
KW - Soil texture
UR - http://www.scopus.com/inward/record.url?scp=85087673573&partnerID=8YFLogxK
U2 - 10.1016/j.geoderma.2020.114562
DO - 10.1016/j.geoderma.2020.114562
M3 - Article
AN - SCOPUS:85087673573
SN - 0016-7061
VL - 376
JO - Geoderma
JF - Geoderma
M1 - 114562
ER -