Redirigiendo al acceso original de articulo en 18 segundos...
Inicio  /  Agriculture  /  Vol: 13 Par: 10 (2023)  /  Artículo
ARTÍCULO
TITULO

Estimation of Total Nitrogen Content in Topsoil Based on Machine and Deep Learning Using Hyperspectral Imaging

Min-Jee Kim    
Jae-Eun Lee    
Insuck Back    
Kyoung Jae Lim and Changyeun Mo    

Resumen

Excessive total nitrogen (TN) content in topsoil is a major cause of eutrophication when nitrogen flows into water systems from soil losses. Therefore, TN content prediction is essential for establishing topsoil management systems and protecting aquatic ecosystems. Recently, hyperspectral imaging (HSI) has been used as a rapid, nondestructive technique for quantifying various soil properties. This study developed a machine and deep learning-based model using hyperspectral imaging to rapidly measure TN contents. A total of 139 topsoil samples were collected from the four major rivers in the Republic of Korea. Visible-to-near-infrared (VNIR) and near-infrared (NIR) hyperspectral imaging data were acquired in the 400?1000 nm and 895?1720 nm ranges, respectively. Prediction models for predicting the TN content in the topsoil were developed using partial least square regression (PLSR) and one-dimensional convolutional neural networks (1D-CNNs). From the total number of pixels in each topsoil sample, 12.5, 25, and 50% of the pixels were randomly selected, and the data were augmented 10 times to improve the performance of the 1D-CNN model. The performances of the models were evaluated by estimating the coefficients of determination (R2) and root mean squared errors (RMSE). The Rp2 values of the optimal PLSR (with maximum normalization preprocessing) and 1D-CNN (with SNV preprocessing) models were 0.72 and 0.92, respectively. Therefore, HSI can be used to estimate TN content in topsoil and build a topsoil database to develop conservation strategies.

 Artículos similares

       
 
Shradha S. Aherkar, Surendra B. Deshmukh, Nitin. M. Konde, Aadinath N. Paslawar, Tanay Joshi, Monika M. Messmer and Amritbir Riar    
The demand for organic cotton is primarily driven by manufacturers and brands with a corporate focus on environmental and social responsibility. These entities strive to be responsible stewards by seeking organic cotton, which not only offers environment... ver más
Revista: Agriculture

 
Allimuthu Elangovan, Nguyen Trung Duc, Dhandapani Raju, Sudhir Kumar, Biswabiplab Singh, Chandrapal Vishwakarma, Subbaiyan Gopala Krishnan, Ranjith Kumar Ellur, Monika Dalal, Padmini Swain, Sushanta Kumar Dash, Madan Pal Singh, Rabi Narayan Sahoo, Govindaraj Kamalam Dinesh, Poonam Gupta and Viswanathan Chinnusamy    
Phenomics technologies have advanced rapidly in the recent past for precision phenotyping of diverse crop plants. High-throughput phenotyping using imaging sensors has been proven to fetch more informative data from a large population of genotypes than t... ver más
Revista: Agriculture

 
Kamila Nowosad, Jan Bocianowski, Farzad Kianersi and Alireza Pour-Aboughadareh    
The assessment of 1000-kernel weight holds significant importance in determining maize grain yield, and elucidating its underlying genetic mechanisms is imperative for enhancing its overall performance. The material for the study consisted of 26 doubled-... ver más
Revista: Agriculture

 
Gamal El Afandi, Hossam Ismael and Souleymane Fall    
Pesticides have been widely used in agriculture, resulting in significant pollution that affects both the environment and human health. This pollution is particularly prevalent in nearby agricultural areas, where sensitive resources are contaminated thro... ver más
Revista: Agriculture

 
Rutuja Rajendra Patil, Sumit Kumar, Shwetambari Chiwhane, Ruchi Rani and Sanjeev Kumar Pippal    
The pathogens such as fungi and bacteria can lead to rice diseases that can drastically impair crop production. Because the illness is difficult to control on a broad scale, crop field monitoring is one of the most effective methods of control. It allows... ver más
Revista: Agriculture