Multisensor Data and Cross-Validation Technique for Merging Temporal Images for the Agricultural Performance Monitoring System

Journal of Food Quality, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 10

Published: April 1, 2022

Many approaches for crop yield prediction were analyzed by countries using remote sensing data, but the information obtained was less successful due to insufficient data gathered climatic variables and poor image resolution. As a result, current estimation methods are obsolete no longer useful. Several attempts have been made overcome these difficulties combining high precision images. Furthermore, such sensing-based working models better suited extraterrestrial farmers homogeneous agricultural areas. The development of this innovative framework prompted scarcity high-quality satellite imagery. This intelligent strategy is based on new theoretical that employs energy equation improve predictions. method used collect input from multiple in order validate observation. proposed technique’s excellent reliability compared contrasted between actual production different areas, meaningful observations provided.

Language: Английский

---

Using Machine-Learning Algorithms to Predict Soil Organic Carbon Content from Combined Remote Sensing Imagery and Laboratory Vis-NIR Spectral Datasets

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(17), P. 4264 - 4264

Published: Aug. 30, 2023

Understanding spatial and temporal variability in soil organic carbon (SOC) content helps simultaneously assess fertility several parameters that are strongly associated with it, such as structural stability, nutrient cycling, biological activity, aeration. Therefore, it appears necessary to monitor SOC regularly investigate rapid, non-destructive, cost-effective approaches for doing so, proximal remote sensing. To increase the accuracy of predictions content, this study evaluated combining sensing time series laboratory spectral measurements using machine deep-learning algorithms. Partial least squares (PLS) regression, random forest (RF), deep neural network (DNN) models were developed Sentinel-2 (S2) 58 sampling points bare according three approaches. In first approach, only S2 bands used calibrate compare performance models. second, indices, Sentinel-1 (S1) S1 moisture added separately during model calibration evaluate their effects individually then together. third, we indices incrementally tested influence on accuracy. Using bands, DNN outperformed PLS RF (ratio interquartile distance RPIQ = 0.79, 1.36 1.67, respectively). Additional information improved performances calibration, yielding most stable improvement among iterations. Including equivalent calculated spectra obtained under conditions prediction SOC, use two achieved good validation (mean 2.01 1.77,

Language: Английский

---

Incorporating agricultural practices in digital mapping improves prediction of cropland soil organic carbon content: The case of the Tuojiang River Basin

Journal of Environmental Management, Journal Year: 2023, Volume and Issue: 330, P. 117203 - 117203

Published: Jan. 3, 2023

Language: Английский

---

Carbon Farming: Bridging Technology Development with Policy Goals

Sustainability, Journal Year: 2024, Volume and Issue: 16(5), P. 1903 - 1903

Published: Feb. 26, 2024

This paper conducts an in-depth exploration of carbon farming at the confluence advanced technology and EU policy, particularly within context European Green Deal. Emphasizing technologies readiness levels (TRL) 6–9, study critically analyzes synthesizes their practical implementation potential in agricultural sector. Methodologically, integrates a review current with analysis policy frameworks, focusing on application these alignment directives. The results demonstrate symbiotic relationship between emerging evolving policies, highlighting how technological advancements can be effectively integrated existing proposed legal structures. is crucial for fostering practical, market-ready, sustainable practices. Significantly, this underscores importance bridging theoretical research commercialization. It proposes pathway transitioning insights into innovative, market-responsive products, thereby contributing to approach not only aligns Deal but also addresses market demands environmental evolution. In conclusion, serves as critical link applications farming. offers comprehensive understanding both landscapes, aiming propel solutions step dynamic goals.

Language: Английский

---

Deep learning models for monitoring landscape changes in a UNESCO Global Geopark

Journal of Environmental Management, Journal Year: 2024, Volume and Issue: 354, P. 120497 - 120497

Published: Feb. 27, 2024

Language: Английский

---

Machine learning-based global trends and the development prospects of wastewater treatment: A bibliometric analysis

Journal of environmental chemical engineering, Journal Year: 2024, Volume and Issue: 12(3), P. 112732 - 112732

Published: April 7, 2024

Language: Английский

---

A critical systematic review on spectral-based soil nutrient prediction using machine learning

Environmental Monitoring and Assessment, Journal Year: 2024, Volume and Issue: 196(8)

Published: July 4, 2024

Language: Английский

---

Remote estimates of soil organic carbon using multi-temporal synthetic images and the probability hybrid model

Geoderma, Journal Year: 2022, Volume and Issue: 425, P. 116066 - 116066

Published: July 29, 2022

Language: Английский

---

A review on digital mapping of soil carbon in cropland: progress, challenge, and prospect

Environmental Research Letters, Journal Year: 2022, Volume and Issue: 17(12), P. 123004 - 123004

Published: Nov. 18, 2022

Abstract Cropland soil carbon not only serves food security but also contributes to the stability of terrestrial ecosystem pool due strong interconnection with atmospheric dioxide. Therefore, better monitoring in cropland is helpful for sequestration and sustainable management. However, severe anthropogenic disturbance mainly gentle terrain creates uncertainty obtaining accurate information limited sample data. Within past 20 years, digital mapping has been recognized as a promising technology carbon. Herein, advance existing knowledge highlight new directions, article reviews research on from 2005 2021. There significant shift linear statistical models machine learning because nonlinear may be more efficient explaining complex soil-environment relationship. Climate covariates parent material play an important role regional scale, while local variability often depends topography, agricultural management, properties. Recently, several kinds have explored based survey or remote sensing technique, while, high resolution remains challenge. Based review, we concluded challenges three categories: sampling, covariates, representation processes models. We thus propose conceptual framework four future strategies: representative sampling strategies, establishing standardized sharing system acquire crop management information, exploring time-series data, well integrating pedological into predictive It intended that this review will support prospective researchers by providing clusters gaps concerning cropland.

Language: Английский

---

Cropland carbon stocks driven by soil characteristics, rainfall and elevation

The Science of The Total Environment, Journal Year: 2022, Volume and Issue: 862, P. 160602 - 160602

Published: Dec. 6, 2022

Language: Английский

---