Application of LW-NIR for rapid prediction of primary nutrients cropland by chemometrics: Comparison among preprocessing and machine learning algorithm approaches
Rapid analytical approaches are necessary for accurate decision-making on the suitability of soil nutrients and types of plants to be cultivated on its cropland. Therefore, in the present study, the potential of long-wave near-infrared spectroscopy (LW-NIRs) as a rapid and nondestructive tool to pre...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | Case Studies in Chemical and Environmental Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666016423001597 |
| _version_ | 1827630308293345280 |
|---|---|
| author | Devianti Sufardi Ramayanty Bulan Nurlaili Oscar Haris |
| author_facet | Devianti Sufardi Ramayanty Bulan Nurlaili Oscar Haris |
| author_sort | Devianti |
| collection | DOAJ |
| description | Rapid analytical approaches are necessary for accurate decision-making on the suitability of soil nutrients and types of plants to be cultivated on its cropland. Therefore, in the present study, the potential of long-wave near-infrared spectroscopy (LW-NIRs) as a rapid and nondestructive tool to predict primary nutrients attributes of soil agriculture including N, P, K was investigated. Five different machine learning algorithms, namely partial least squares regression (PLSR), k-nearest neighbor (kNN), decision tree (DT), adaboosting (AB), and Gaussian process regression (GPR) were used and compared to predict the N, P, K content of cropland from Aceh Province. These prediction models were established based on NIR spectra acquired in the wavelength range from 1100 to 2000 nm. Four different preprocessing transformations including standard normal variate (SNV), multiplicative scatter correction (MSC), first derivative (D1) and second derivative (D2) were applied as spectra enhancement prior to prediction model development. The results obtained show that the SNV preprocessing followed by kNN is better than any other preprocessing approach and machine learning algorithm for the prediction of N, P, K content. The optimal prediction model for N and P content attributes were obtained by kNN with the closest neighbor of 4 components as a the best hyperparameter and the two components for prediction K content attribute prediction. The model's performance using the ratio of prediction to deviation (RPD) to predict N, P, K content attributes was higher than 7. The overall results satisfactorily demonstrate that NIRs technology combined with proper preprocessing and regression approaches has promising results to determine primary nutrients attributes of soil agriculture nondestructively. |
| first_indexed | 2024-03-09T14:04:00Z |
| format | Article |
| id | doaj.art-7d2364b5d20747cdbcea3e36c16241b3 |
| institution | Directory Open Access Journal |
| issn | 2666-0164 |
| language | English |
| last_indexed | 2024-03-09T14:04:00Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Case Studies in Chemical and Environmental Engineering |
| spelling | doaj.art-7d2364b5d20747cdbcea3e36c16241b32023-11-30T05:11:05ZengElsevierCase Studies in Chemical and Environmental Engineering2666-01642023-12-018100454Application of LW-NIR for rapid prediction of primary nutrients cropland by chemometrics: Comparison among preprocessing and machine learning algorithm approaches Devianti0 Sufardi1Ramayanty Bulan2 Nurlaili3Oscar Haris4Department of Agricultural Engineering, Faculty of Agriculture, Syiah Kuala University, Banda Aceh, 23111, Indonesia; Corresponding author.Department of Soil Science, Faculty of Agriculture, Syiah Kuala University, Banda Aceh, 23111, IndonesiaDepartment of Agricultural Engineering, Faculty of Agriculture, Syiah Kuala University, Banda Aceh, 23111, IndonesiaDepartment of Mechanical Engineering, Politeknik Negeri Lhokseumawe, Lhokseumawe, 24301, IndonesiaDepartment of Automotive Industrial Engineering Technology, Boash Indonesia Digital Polytechnic, 16310, Bogor, IndonesiaRapid analytical approaches are necessary for accurate decision-making on the suitability of soil nutrients and types of plants to be cultivated on its cropland. Therefore, in the present study, the potential of long-wave near-infrared spectroscopy (LW-NIRs) as a rapid and nondestructive tool to predict primary nutrients attributes of soil agriculture including N, P, K was investigated. Five different machine learning algorithms, namely partial least squares regression (PLSR), k-nearest neighbor (kNN), decision tree (DT), adaboosting (AB), and Gaussian process regression (GPR) were used and compared to predict the N, P, K content of cropland from Aceh Province. These prediction models were established based on NIR spectra acquired in the wavelength range from 1100 to 2000 nm. Four different preprocessing transformations including standard normal variate (SNV), multiplicative scatter correction (MSC), first derivative (D1) and second derivative (D2) were applied as spectra enhancement prior to prediction model development. The results obtained show that the SNV preprocessing followed by kNN is better than any other preprocessing approach and machine learning algorithm for the prediction of N, P, K content. The optimal prediction model for N and P content attributes were obtained by kNN with the closest neighbor of 4 components as a the best hyperparameter and the two components for prediction K content attribute prediction. The model's performance using the ratio of prediction to deviation (RPD) to predict N, P, K content attributes was higher than 7. The overall results satisfactorily demonstrate that NIRs technology combined with proper preprocessing and regression approaches has promising results to determine primary nutrients attributes of soil agriculture nondestructively.http://www.sciencedirect.com/science/article/pii/S2666016423001597ChemometricsLand nutrientsNon-destructive measurementsPrecisionTropical cropland |
| spellingShingle | Devianti Sufardi Ramayanty Bulan Nurlaili Oscar Haris Application of LW-NIR for rapid prediction of primary nutrients cropland by chemometrics: Comparison among preprocessing and machine learning algorithm approaches Case Studies in Chemical and Environmental Engineering Chemometrics Land nutrients Non-destructive measurements Precision Tropical cropland |
| title | Application of LW-NIR for rapid prediction of primary nutrients cropland by chemometrics: Comparison among preprocessing and machine learning algorithm approaches |
| title_full | Application of LW-NIR for rapid prediction of primary nutrients cropland by chemometrics: Comparison among preprocessing and machine learning algorithm approaches |
| title_fullStr | Application of LW-NIR for rapid prediction of primary nutrients cropland by chemometrics: Comparison among preprocessing and machine learning algorithm approaches |
| title_full_unstemmed | Application of LW-NIR for rapid prediction of primary nutrients cropland by chemometrics: Comparison among preprocessing and machine learning algorithm approaches |
| title_short | Application of LW-NIR for rapid prediction of primary nutrients cropland by chemometrics: Comparison among preprocessing and machine learning algorithm approaches |
| title_sort | application of lw nir for rapid prediction of primary nutrients cropland by chemometrics comparison among preprocessing and machine learning algorithm approaches |
| topic | Chemometrics Land nutrients Non-destructive measurements Precision Tropical cropland |
| url | http://www.sciencedirect.com/science/article/pii/S2666016423001597 |
| work_keys_str_mv | AT devianti applicationoflwnirforrapidpredictionofprimarynutrientscroplandbychemometricscomparisonamongpreprocessingandmachinelearningalgorithmapproaches AT sufardi applicationoflwnirforrapidpredictionofprimarynutrientscroplandbychemometricscomparisonamongpreprocessingandmachinelearningalgorithmapproaches AT ramayantybulan applicationoflwnirforrapidpredictionofprimarynutrientscroplandbychemometricscomparisonamongpreprocessingandmachinelearningalgorithmapproaches AT nurlaili applicationoflwnirforrapidpredictionofprimarynutrientscroplandbychemometricscomparisonamongpreprocessingandmachinelearningalgorithmapproaches AT oscarharis applicationoflwnirforrapidpredictionofprimarynutrientscroplandbychemometricscomparisonamongpreprocessingandmachinelearningalgorithmapproaches |