Convolutional neural networks-based health risk modelling of some heavy metals in a soil-rice system

Li, Panpan; Hao, Huijuan; Bai, Yang; Li, Yuanyuan; Mao, Xiaoguang; Xu, Jianjun; Li, Meng; Lv, Yuntao; Chen, Wan-Ming; Ge, Dabing

doi:10.1016/j.scitotenv.2022.156466

Cited by 12 publications

(3 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, only As, Cd, Pb, and Ni were included in the calculation of CR , as they were identified as carcinogens by the USEPA [ 48 ]. The SF values for As, Cd, Pb, and Ni are 1.5, 6.3, 0.0085, and 0.84 mg kg −1 day −1 , respectively [ 28 , 49 , 50 ]. CR values greater than 1 × 10 −4 indicate that there is a high probability of the occurrence of cancer risk in the population [ 51 ].…”

Section: Methodsmentioning

confidence: 99%

Detection of Heavy Metals, Their Distribution in Tilapia spp., and Health Risks Assessment

Mendoza

Nolos

Villaflores

et al. 2023

Toxics

View full text Add to dashboard Cite

Concentrations of heavy metals (HMs) were assessed in Tilapia spp. from selected communities in Calapan City, Philippines. Eleven (11) inland farmed tilapia samples were collected and analyzed for HMs concentration using X-ray fluorescence (XRF). The 11 fish samples were cut into seven pieces, according to the fish body parts, constituting a total of 77 samples. These fish samples were then labeled as bone, fins, head, meat, skin, and viscera. Results showed that the mean concentration of Cd in all parts of tilapia exceeded the Food and Agriculture Organization/World Health Organization (FAO/WHO) limits. The highest concentration was recorded in the fins, which was sevenfold higher than the limit. The trend of the mean concentration of Cd in different parts of tilapia was fins > viscera > skin > tail > head > meat > bone. The target hazard quotient (THQ) recorded a value less than 1. This means that the population exposed to tilapia, within the area where fish samples originated, were not at risk to non-carcinogens. The concentrations of Cu, Pb, Mn, Hg, and Zn in different parts, particularly in skin, fins, and viscera, also exceeded the FAO/WHO limits. The calculated cancer risk (CR) in consuming the fish skin, meat, fins, bone, viscera, and head was higher than the USEPA limit. This indicated a possible carcinogenic risk when consumed regularly. Most of the correlations observed between HMs in various parts of the tilapia had positive (direct) relationships, which were attributed to the HM toxicity target organ characteristics. Results of the principal component analysis (PCA) showed that most of the dominating HMs recorded in tilapia were attributable to anthropogenic activities and natural weathering within the watershed of agricultural areas. The agriculture area comprises about 86.83% of the overall land area of Calapan City. The identified carcinogenic risks were associated with Cd. Therefore, regular monitoring of HMs in inland fishes, their habitat, and surface water quality shall be carried out. This information is useful in creating strategies in metals concentration monitoring, health risks reduction program, and relevant guidelines that would reduce the accumulation of HM in fish.

show abstract

Section: Methodsmentioning

confidence: 99%

Detection of Heavy Metals, Their Distribution in Tilapia spp., and Health Risks Assessment

Mendoza

Nolos

Villaflores

et al. 2023

Toxics

View full text Add to dashboard Cite

show abstract

“…Extreme Gradient Boosting (XGBoost) was learning from parameters in the same way as the regression tree family approach. This model was based on the gradient descent direction of the loss function of the last established model [31], as explained by the following equation: The R-Squared represents the relationship between independent and dependent variables, while the Root-Mean-Square Error (RMSE) and the Mean of Absolute value of Errors (MAE) represent the relationship between predicted crop yields and observed crop yields of 20 sample plots [32] and [33], as illustrated by the following equation:…”

Section: Methodsmentioning

confidence: 99%

The Application of Unmanned Aerial Vehicles (UAVs) and Extreme Gradient Boosting (XGBoost) to Crop Yield Estimation: A Case Study of Don Tum District, Nakhon Pathom, Thailand

2023

IJG

View full text Add to dashboard Cite

Rice (Oryza sativa L.) is a staple food for more than half of the global population. This research, therefore, aims to explore the estimation of crop yields towards the application of unmanned aerial vehicles (UAVs). The research areas are the sample rice fields owned by Sam Ngam Large-Scale Rice Production Community Enterprise in Don Tum District, Nakhon Pathom. The data collected by both RGB and multispectral UAVs was used for estimating the crop yields of Rice Department 41 (RD41), a rice variety, and then analyzed by a geographic information system (GIS). Multiple Linear Regression was applied to factor analysis for the purpose of crop yield estimation based on the factors investigated and obtained by the UAVs. These factors included vegetation indexes (i.e. Normalized Difference Vegetation Index, Green Normalized Difference Vegetation Index, and Triangular Greenness Index), plant height, and canopy coverage. The prediction of the analysis model was proved to be valid (R2 = 0.99; RMSE = 2.506 g.). Extreme Gradient Boosting (XGBoost) was applied to increase the accuracy of the estimation (RMSE = 0.557 g.; MAE = 0.364). The findings of study showed that the utilization of UAVs could contribute to the estimation of crop yield in the research areas.

show abstract

“…For instance, Xu et al [145] used an ensemble model by optimized SVM (R 2 = 0.88) to estimate Zn concentration in polluted soils of Shandong province in China. In addition, deep learning methods extend the envelope of knowledge by using artificial neural networks (ANN), convolutional neural networks (CNN), and convolutional long short-term memory (Conv LSTM) in extracting deep features from complex multi-source datasets through multiple kernel learning [146,147] and therefore, provide improved accuracy and prediction capabilities. Bazoobandi et al [148] improved the R 2 of soil Cd and Pb content prediction from 0.47 obtained by multiple linear regression (MLR) to 0.83 using ANN and identified soil organic carbon (SOC) as the most significant factor.…”

Section: Phytogeochemistry Integrative Exploration Approachesmentioning

confidence: 99%

Geochemistry of Terrestrial Plants in the Central African Copperbelt: Implications for Sediment Hosted Copper-Cobalt Exploration

Mukube,

Hitzman,

Machogo-Phao

et al. 2024

Minerals

View full text Add to dashboard Cite

Mineral exploration has increasingly targeted areas covered by in situ or transported overburden for shallow to deep-seated orebodies. It remains critical to develop better means to detect the surficial chemical footprint of mineralized areas covered by thick regolith. In such settings, plant geochemistry could potentially be a useful exploration tool, as different plant species have varying degrees of tolerance to metal enrichment in the soil. This review provides insights into the geological and geochemical controls on metal accumulation patterns in soil–plant systems of the Central African Copperbelt. In addition, it highlights the opportunities for integrating the geochemistry of terrestrial plants in emerging exploration technologies, identifies research gaps, and suggests future directions for developing phytogeochemical sampling techniques. This review was conducted using reputable online scholarly databases targeting original research articles published between January 2005 and March 2023, from which selected articles were identified, screened, and used to explore current advances, opportunities, and future directions for the use of plant geochemistry in sediment hosted Cu–Co exploration in the Central African Copperbelt. Various plant species are recognized as ore deposit indicators through either independent phytogeochemistry or complementary approaches. In the Central African Copperbelt, the successful application of hyperaccumulator species for phytoremediation provides the basis for adopting phytogeochemistry in mineral exploration. Furthermore, current advances in remote sensing, machine learning, and deep learning techniques could enable multi-source data integration and allow for the integration of phytogeochemistry.

show abstract

Convolutional neural networks-based health risk modelling of some heavy metals in a soil-rice system

Cited by 12 publications

References 60 publications

Detection of Heavy Metals, Their Distribution in Tilapia spp., and Health Risks Assessment

Detection of Heavy Metals, Their Distribution in Tilapia spp., and Health Risks Assessment

The Application of Unmanned Aerial Vehicles (UAVs) and Extreme Gradient Boosting (XGBoost) to Crop Yield Estimation: A Case Study of Don Tum District, Nakhon Pathom, Thailand

Geochemistry of Terrestrial Plants in the Central African Copperbelt: Implications for Sediment Hosted Copper-Cobalt Exploration

Contact Info

Product

Resources

About