1
|
Zarei M, Solomatova NV, Aghaei H, Rothwell A, Wiens J, Melo L, Good TG, Shokatian S, Grant E. Machine Learning Analysis of Raman Spectra To Quantify the Organic Constituents in Complex Organic-Mineral Mixtures. Anal Chem 2023; 95:15908-15916. [PMID: 37698955 PMCID: PMC10620774 DOI: 10.1021/acs.analchem.3c02348] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2023] [Accepted: 08/25/2023] [Indexed: 09/14/2023]
Abstract
Important decisions in local agricultural policy and practice often hinge on the soil's chemical composition. Raman spectroscopy offers a rapid noninvasive means to quantify the constituents of complex organic systems. But the application of Raman spectroscopy to soils presents a multifaceted challenge due to organic/mineral compositional complexity and spectral interference arising from overwhelming fluorescence. The present work compares methodologies with the capacity to help overcome common obstacles that arise in the analysis of soils. We created conditions representative of these challenges by combining varying proportions of six amino acids commonly found in soils with fluorescent bentonite clay and coarse mineral components. Referring to an extensive data set of Raman spectra, we compare the performance of the convolutional neural network (CNN) and partial least-squares regression (PLSR) multivariate models for amino acid composition. Strategies employing volume-averaged spectral sampling and data preprocessing algorithms improve the predictive power of these models. Our average test R2 for PLSR models exceeds 0.89 and approaches 0.98, depending on the complexity of the matrix, whereas CNN yields an R2 range from 0.91 to 0.97, demonstrating that classic PLSR and CNN perform comparably, except in cases where the signal-to-noise ratio of the organic component is very low, whereupon CNN models outperform. Artificially isolating two of the most prevalent obstacles in evaluating the Raman spectra of soils, we have characterized the effect of each obstacle on the performance of machine learning models in the absence of other complexities. These results highlight important considerations and modeling strategies necessary to improve the Raman analysis of organic compounds in complex mixtures in the presence of mineral spectral components and significant fluorescence.
Collapse
Affiliation(s)
- Mahsa Zarei
- Department
of Chemistry, The University of British
Columbia, 2036 Main Mall, Vancouver, British Columbia V6T 1Z1, Canada
| | - Natalia V. Solomatova
- Miraterra
Technologies Corporation, 199 W 6th Ave, Vancouver, British Columbia V5Y 1K3, Canada
| | - Hoda Aghaei
- Miraterra
Technologies Corporation, 199 W 6th Ave, Vancouver, British Columbia V5Y 1K3, Canada
| | - Austin Rothwell
- Miraterra
Technologies Corporation, 199 W 6th Ave, Vancouver, British Columbia V5Y 1K3, Canada
| | - Jeffrey Wiens
- Miraterra
Technologies Corporation, 199 W 6th Ave, Vancouver, British Columbia V5Y 1K3, Canada
| | - Luke Melo
- Department
of Chemistry, The University of British
Columbia, 2036 Main Mall, Vancouver, British Columbia V6T 1Z1, Canada
| | - Travis G. Good
- Miraterra
Technologies Corporation, 199 W 6th Ave, Vancouver, British Columbia V5Y 1K3, Canada
| | - Sadegh Shokatian
- Miraterra
Technologies Corporation, 199 W 6th Ave, Vancouver, British Columbia V5Y 1K3, Canada
| | - Edward Grant
- Department
of Chemistry, The University of British
Columbia, 2036 Main Mall, Vancouver, British Columbia V6T 1Z1, Canada
| |
Collapse
|
2
|
Wu H, Le QN, Zeng B, Zhang X. Nanoextraction from a flow of a highly diluted solution for much-improved sensitivity in offline chemical detection and quantification. Anal Chim Acta 2023; 1274:341529. [PMID: 37455069 DOI: 10.1016/j.aca.2023.341529] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2023] [Revised: 05/13/2023] [Accepted: 06/12/2023] [Indexed: 07/18/2023]
Abstract
Preconcentration of the target compound is a critical step that ensures the accuracy of the subsequent chemical analysis. In this work, we present a straightforward yet effective liquid-liquid extraction approach based on surface nanodroplets (i.e., nanoextraction) for offline analysis of highly diluted sample solutions. The extraction and sample collection were streamlined in a 3-m microcapillary tube. The concentration of the target analyte in surface nanodroplets was significantly increased compared to the concentration in the sample solution, reaching several orders of magnitude. A limit of detection (LOD) was decreased by a factor of ∼103 for an organic model compound in Fourier-transform infrared spectroscopy (FTIR) measurements and ∼105 for a model fluorescent dye in fluorescence detection. The quantitative analysis of the organic compound was also achieved in a wide concentration region from 10-3 M to 10-4 M. The total volume of surface nanodroplets can be manipulated to further enhance extraction efficiency, according to the principle that governs droplet formation by solvent exchange. Additionally, our method exhibited significantly improved sensitivity compared to traditional dispersive liquid-liquid microextraction (DLLME). The LOD of the fluorescent dye and the organic model compound obtained with DLLME was 3 orders of magnitude and 20 times higher than the LOD achieved through nanoextraction approach. The nanoextraction developed in this work can be applied to preconcentrate multi-compounds from river water samples, without clear interference from each other. This can further extend its applicability for the detection and quantification of target analytes in complex aqueous samples by common analytical instruments.
Collapse
Affiliation(s)
- Hongyan Wu
- Department of Chemical and Materials Engineering, University of Alberta, Alberta, T6G 1H9, Canada
| | - Quynh Nhu Le
- Department of Chemical and Materials Engineering, University of Alberta, Alberta, T6G 1H9, Canada
| | - Binglin Zeng
- Department of Chemical and Materials Engineering, University of Alberta, Alberta, T6G 1H9, Canada
| | - Xuehua Zhang
- Department of Chemical and Materials Engineering, University of Alberta, Alberta, T6G 1H9, Canada; Physics of Fluids Group, Max Planck Center Twente for Complex Fluid Dynamics, JM Burgers Center for Fluid Dynamics, Mesa+, Department of Science and Technology, University of Twente, Enschede, 7522 NB, the Netherlands.
| |
Collapse
|
3
|
Li Q, Hu W, Li L, Li Y. Interactions between organic matter and Fe oxides at soil micro-interfaces: Quantification, associations, and influencing factors. THE SCIENCE OF THE TOTAL ENVIRONMENT 2023; 855:158710. [PMID: 36099954 DOI: 10.1016/j.scitotenv.2022.158710] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/21/2022] [Revised: 09/05/2022] [Accepted: 09/08/2022] [Indexed: 06/15/2023]
Abstract
Iron (Fe) oxides are widely recognized to prevent the degradation of organic matter (OM) in environments, thereby promoting the persistence of organic carbon (OC) in soils. Thus, discerning the association mechanisms of Fe oxides and OC interactions is key to effectively influencing the dynamics and extent of organic C cycling in soils. Previous studies have focused on i) quantifying Fe oxide-bound organic carbon (Fe-OC) in individual environments, ii) investigating the distribution and adsorption capacity of Fe-OC, and iii) assessing the redox cycling and transformation of Fe-OC. Furthermore, the widespread application of high-tech instrumentation and methods has greatly contributed to a better understanding of the mechanism of organic mineral assemblages in the past few decades. However, few literature reviews have comprehensively summarized Fe-OC distributions, associations, and characteristics in soil-plant systems. Here, studies investigating the Fe-OC contents among different environments are reviewed. In addition, the mechanisms and processes related to OM transformation dynamics occurring at mineral-organic interfaces are also described. Recent studies have highlighted that diverse interactions occur between Fe oxides and OC, with organic compounds adhering to Fe oxides due to their huge specific surfaces area and active reaction sites. Moreover, we also review methods for understanding Fe-OC interactions at micro-interfaces. Lastly, developmental prospects for understanding coupled Fe-OC geochemical processes in soil environments at molecular- and nano-scales are outlined. The summary suggests that combined advanced techniques and methods should be used in future research to explore micro-interfaces and in situ descriptions of organic mineral assemblages. This review also suggests that future studies need to consider the functional and spatial complexity that is typical of soil/sediment environments where Fe-OC interactions occur.
Collapse
Affiliation(s)
- Qi Li
- Institute of Agricultural Resources and Environment, Guangdong Academy of Agricultural Sciences, Guangzhou 510640, China; Key Laboratory of Plant Nutrition and Fertilizer in South Region, Ministry of Agriculture, Guangzhou 510640, China; Guangdong Key Laboratory of Nutrient Cycling and Farmland Conservation, Guangzhou 510640, China
| | - Weifang Hu
- Institute of Agricultural Resources and Environment, Guangdong Academy of Agricultural Sciences, Guangzhou 510640, China; Key Laboratory of Plant Nutrition and Fertilizer in South Region, Ministry of Agriculture, Guangzhou 510640, China; Guangdong Key Laboratory of Nutrient Cycling and Farmland Conservation, Guangzhou 510640, China
| | - Linfeng Li
- Institute of Agricultural Resources and Environment, Guangdong Academy of Agricultural Sciences, Guangzhou 510640, China; Key Laboratory of Plant Nutrition and Fertilizer in South Region, Ministry of Agriculture, Guangzhou 510640, China; Guangdong Key Laboratory of Nutrient Cycling and Farmland Conservation, Guangzhou 510640, China
| | - Yichun Li
- Institute of Agricultural Resources and Environment, Guangdong Academy of Agricultural Sciences, Guangzhou 510640, China; Key Laboratory of Plant Nutrition and Fertilizer in South Region, Ministry of Agriculture, Guangzhou 510640, China; Guangdong Key Laboratory of Nutrient Cycling and Farmland Conservation, Guangzhou 510640, China.
| |
Collapse
|
4
|
Peng L, Wang Y. Sediment organic carbon dominates the heteroaggregation of suspended sediment and nanoplastics in natural and surfactant-polluted aquatic environments. JOURNAL OF HAZARDOUS MATERIALS 2022; 440:129802. [PMID: 36007369 DOI: 10.1016/j.jhazmat.2022.129802] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/23/2022] [Revised: 07/27/2022] [Accepted: 08/16/2022] [Indexed: 06/15/2023]
Abstract
The aggregation of nanoplastics (NPs) and suspended sediment (SPS) is the key to the transport and environmental fate of NPs. However, the influence of SPS composition and environmental conditions on this process and its mechanisms are still unclear. In this study, the heteroaggregation of NPs and SPS of different compositions is systematically explored under natural and surfactant-polluted aquatic environments (NaCl, humic acid, cetyltrimethylammonium bromide (CTAB)). The results showed that sediment organic carbon (SOC) dominates the aggregation and that different kinds of SOC (comprised of both amorphous organic carbon (AOC) and black carbon (BC)) contribute vary under distinct conditions. In natural freshwater, AOC represents a larger contribution to aggregation because of its weaker electrostatic repulsion compared to that of BC. However, BC represents a larger contribution in natural seawater resulting from decreased electrostatic repulsion and more hydrogen bonding. Conversely, in surfactant-polluted aquatic environments, both AOC and BC have a high contribution owing to the bridge effect plus hydrogen bonding. Notably, minerals' contribution in aggregates remains low under all conditions. Furthermore, CTAB typically inhibits aggregation except under special conditions. The findings of this study contribute notably to a better understanding of the migration of nanoplastics in complex aquatic environments.
Collapse
Affiliation(s)
- Ling Peng
- The Key Laboratory of Water and Sediment Sciences, Ministry of Education, School of Environment, Beijing Normal University, Beijing 100875, PR China.
| | - Ying Wang
- The Key Laboratory of Water and Sediment Sciences, Ministry of Education, School of Environment, Beijing Normal University, Beijing 100875, PR China.
| |
Collapse
|
5
|
Ma L, Zhao L, Cao L, Li D, Chen G, Han Y. Inversion of Soil Organic Matter Content Based on Improved Convolutional Neural Network. SENSORS (BASEL, SWITZERLAND) 2022; 22:7777. [PMID: 36298127 PMCID: PMC9610480 DOI: 10.3390/s22207777] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/15/2022] [Revised: 10/01/2022] [Accepted: 10/08/2022] [Indexed: 06/16/2023]
Abstract
Soil organic matter (SOM) is an important source of nutrients required during crop growth and is an important component of cultivated soil. In this paper, we studied the possibility of using deep learning methods to establish a multi-feature model to predict SOM content. Moreover, using Nong'an County of Changchun City as the study area, Sentinel-2A remote sensing images were taken as the data source to construct the dataset by using field sampling and image processing. The LeNet-5 convolutional neural network model was chosen as the deep learning model, which was improved based on the basic model. The evaluation metrics were selected as the root mean square error (RMSE) and the coefficient of determination R2. Through comparison, the R2 of the improved model was found to be higher than that of the linear regression method, Support Vector Machines (SVM) (RMSE = 2.471, R2 = 0.4035), and Random Forest (RF) (RMSE = 2.577, R2 = 0.4913). The result shows that: (1) It is feasible to use the multispectral data extracted from remote sensing images for soil organic matter content inversion based on the deep learning model with a minimum RMSE of 2.979 and with the R2 reaching 0.89. (2) The choice of features has an impact on the prediction of the model to a certain extent. After ranking the importance of features, selecting the appropriate number of features for inversion provides better results than full feature inversion, and the computational speed is improved.
Collapse
Affiliation(s)
- Li Ma
- College of Information and Technology, Jilin Agricultural University, Changchun 130118, China
- Institute for the Smart Agriculture, Jilin Agricultural University, Changchun 130117, China
| | - Lei Zhao
- College of Information and Technology, Jilin Agricultural University, Changchun 130118, China
| | - Liying Cao
- College of Information and Technology, Jilin Agricultural University, Changchun 130118, China
- Institute for the Smart Agriculture, Jilin Agricultural University, Changchun 130117, China
| | - Dongming Li
- College of Information and Technology, Jilin Agricultural University, Changchun 130118, China
- Institute for the Smart Agriculture, Jilin Agricultural University, Changchun 130117, China
| | - Guifen Chen
- Institute of Technology, Changchun Humanities and Sciences College, Changchun 130118, China
| | - Ye Han
- College of Information and Technology, Jilin Agricultural University, Changchun 130118, China
- Institute for the Smart Agriculture, Jilin Agricultural University, Changchun 130117, China
| |
Collapse
|
6
|
Near-infrared spectroscopy and machine learning for classification of food powders under moving conditions. J FOOD ENG 2022. [DOI: 10.1016/j.jfoodeng.2022.111339] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
|
7
|
Sun M, Li Q, Jiang X, Ye T, Li X, Niu B. Estimation of Soil Salt Content and Organic Matter on Arable Land in the Yellow River Delta by Combining UAV Hyperspectral and Landsat-8 Multispectral Imagery. SENSORS 2022; 22:s22113990. [PMID: 35684611 PMCID: PMC9183165 DOI: 10.3390/s22113990] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/28/2022] [Revised: 05/14/2022] [Accepted: 05/23/2022] [Indexed: 02/06/2023]
Abstract
Rapid and large-scale estimation of soil salt content (SSC) and organic matter (SOM) using multi-source remote sensing is of great significance for the real-time monitoring of arable land quality. In this study, we simultaneously predicted SSC and SOM on arable land in the Yellow River Delta (YRD), based on ground measurement data, unmanned aerial vehicle (UAV) hyperspectral imagery, and Landsat-8 multispectral imagery. The reflectance averaging method was used to resample UAV hyperspectra to simulate the Landsat-8 OLI data (referred to as fitted multispectra). Correlation analyses and the multiple regression method were used to construct SSC and SOM hyperspectral/fitted multispectral estimation models. Then, the best SSC and SOM fitted multispectral estimation models based on UAV images were applied to a reflectance-corrected Landsat-8 image, and SSC and SOM distributions were obtained for the YRD. The estimation results revealed that moderately salinized arable land accounted for the largest proportion of area in the YRD (48.44%), with the SOM of most arable land (60.31%) at medium or lower levels. A significant negative spatial correlation was detected between SSC and SOM in most regions. This study integrates the advantages of UAV hyperspectral and satellite multispectral data, thereby realizing rapid and accurate estimation of SSC and SOM for a large-scale area, which is of great significance for the targeted improvement of arable land in the YRD.
Collapse
Affiliation(s)
- Mingyue Sun
- College of Resources and Environment, Shandong Agricultural University, Taian 271018, China; (M.S.); (X.J.); (T.Y.); (X.L.)
| | - Qian Li
- Department of Applied Mathematics and Statistics, Stony Brook University, New York, NY 11794, USA;
| | - Xuzi Jiang
- College of Resources and Environment, Shandong Agricultural University, Taian 271018, China; (M.S.); (X.J.); (T.Y.); (X.L.)
| | - Tiantian Ye
- College of Resources and Environment, Shandong Agricultural University, Taian 271018, China; (M.S.); (X.J.); (T.Y.); (X.L.)
| | - Xinju Li
- College of Resources and Environment, Shandong Agricultural University, Taian 271018, China; (M.S.); (X.J.); (T.Y.); (X.L.)
| | - Beibei Niu
- College of Resources and Environment, Shandong Agricultural University, Taian 271018, China; (M.S.); (X.J.); (T.Y.); (X.L.)
- Correspondence: ; Tel.: +86-132-2062-8537
| |
Collapse
|