東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Explainable Artificial Intelligence ...

An, Di,

Linked to FindBook

Google Book

Amazon

博客來

Explainable Artificial Intelligence Internet of Things (XAIoT) Enabled Smart Sensing of Soil Carbon Content for Smart Application of Biochar /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Explainable Artificial Intelligence Internet of Things (XAIoT) Enabled Smart Sensing of Soil Carbon Content for Smart Application of Biochar // Di An.
Author:	An, Di,
Description:	1 electronic resource (286 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-01, Section: B.
Contained By:	Dissertations Abstracts International86-01B.
Subject:	Computer science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31243487
ISBN:	9798383566893

Explainable Artificial Intelligence Internet of Things (XAIoT) Enabled Smart Sensing of Soil Carbon Content for Smart Application of Biochar /
An, Di,

Explainable Artificial Intelligence Internet of Things (XAIoT) Enabled Smart Sensing of Soil Carbon Content for Smart Application of Biochar /Di An. - 1 electronic resource (286 pages)

Source: Dissertations Abstracts International, Volume: 86-01, Section: B.

Soil carbon content is vital to the way ecosystems function, and it plays an important role in soil properties in producing food, storing water, and mitigating climate change. Soil carbon is the key to unlocking the soil's various economic and environmental benefits, often known as the multi-functionality of soil carbon content. Human activities, particularly those that include the use of fire to burn biomass, deplete soil cover and result in immediate and enduring losses of soil organic carbon. We must minimize soil carbon loss due to erosion and greenhouse gas (GHG) emissions into the environment. As a way to capture and store carbon dioxide in the atmosphere, carbon sequestration can be used as a way to adapt to climate change because it has been shown to have positive effects on temperature, gross primary production, and the ability of soil to hold water. However, it is still a challenging problem to quantify the effect of how much carbon (biochar) is applied to the soil in terms of carbon sequestration accurately, quickly, cost-effectively, and on a large-scale field. Many studies use expensive element analyzers with intensive labor costs to measure soil carbon content. Several research efforts include utilizing artificial intelligence methods or applications to acquire carbon information from the soil and the atmosphere but lacking proper human interpretation (domain knowledge), the results might not be reliable. Therefore, Explainable Artificial Intelligence of the Internet of Things (XAIoT) is proposed to address the reliability issue and define a set of AI models that are interpretable by domain knowledge from environmental and engineering domain experts. Furthermore, the objectives that we would like to achieve are: 1) the XAIoT empowered microwave and millimeter-wave radar sensing as systematic data acquisition platforms for measuring soil carbon content; 2) in situ site-specific management (SSM) systems to manage soil carbon content and using machine learning algorithms; 3) the Digital Twin-enabled optimal soil carbon content management strategy in large-scale fields using mobile platforms such as UAVs and UGVs for the application of biochar and manure mixtures; 4) a cognitive battery management system for extending battery life for XAIoT smart sensing and smart actuation subsystems. The proposed applications and solutions have the positive potential to fight climate change, reduce carbon emissions, strengthen the quality of life on low-income and disadvantaged farms and adjacent communities, and identify means to gain acceptance among stakeholders in soil carbon management.

English

ISBN: 9798383566893Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Carbon negative technologies

Explainable Artificial Intelligence Internet of Things (XAIoT) Enabled Smart Sensing of Soil Carbon Content for Smart Application of Biochar /
LDR:04151nmm a22004333i 4500 001 2431255
005 20250603111415.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798383566893
035 $a (MiAaPQD)AAI31243487
035 $a AAI31243487
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a An, Di, $e author. $3 3819975
245 1 0 $a Explainable Artificial Intelligence Internet of Things (XAIoT) Enabled Smart Sensing of Soil Carbon Content for Smart Application of Biochar / $c Di An.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (286 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-01, Section: B.
500 $a Advisors: Chen, YangQuan Committee members: Singhal, Mukesh; Li, Dong; Diaz, Gerardo.
502 $b Ph.D. $c University of California, Merced $d 2024.
520 $a Soil carbon content is vital to the way ecosystems function, and it plays an important role in soil properties in producing food, storing water, and mitigating climate change. Soil carbon is the key to unlocking the soil's various economic and environmental benefits, often known as the multi-functionality of soil carbon content. Human activities, particularly those that include the use of fire to burn biomass, deplete soil cover and result in immediate and enduring losses of soil organic carbon. We must minimize soil carbon loss due to erosion and greenhouse gas (GHG) emissions into the environment. As a way to capture and store carbon dioxide in the atmosphere, carbon sequestration can be used as a way to adapt to climate change because it has been shown to have positive effects on temperature, gross primary production, and the ability of soil to hold water. However, it is still a challenging problem to quantify the effect of how much carbon (biochar) is applied to the soil in terms of carbon sequestration accurately, quickly, cost-effectively, and on a large-scale field. Many studies use expensive element analyzers with intensive labor costs to measure soil carbon content. Several research efforts include utilizing artificial intelligence methods or applications to acquire carbon information from the soil and the atmosphere but lacking proper human interpretation (domain knowledge), the results might not be reliable. Therefore, Explainable Artificial Intelligence of the Internet of Things (XAIoT) is proposed to address the reliability issue and define a set of AI models that are interpretable by domain knowledge from environmental and engineering domain experts. Furthermore, the objectives that we would like to achieve are: 1) the XAIoT empowered microwave and millimeter-wave radar sensing as systematic data acquisition platforms for measuring soil carbon content; 2) in situ site-specific management (SSM) systems to manage soil carbon content and using machine learning algorithms; 3) the Digital Twin-enabled optimal soil carbon content management strategy in large-scale fields using mobile platforms such as UAVs and UGVs for the application of biochar and manure mixtures; 4) a cognitive battery management system for extending battery life for XAIoT smart sensing and smart actuation subsystems. The proposed applications and solutions have the positive potential to fight climate change, reduce carbon emissions, strengthen the quality of life on low-income and disadvantaged farms and adjacent communities, and identify means to gain acceptance among stakeholders in soil carbon management.
546 $a English
590 $a School code: 1660
650 4 $a Computer science. $3 523869
650 4 $a Environmental engineering. $3 548583
650 4 $a Agricultural engineering. $3 3168406
653 $a Carbon negative technologies
653 $a Digital twin
653 $a Proximal soil sensing
653 $a Site Specific Management
653 $a Smart sensing
690 $a 0984
690 $a 0539
690 $a 0775
710 2 $a University of California, Merced. $b Electrical Engineering and Computer Science. $e degree granting institution. $3 3819976
720 1 $a Chen, YangQuan $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-01B.
790 $a 1660
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31243487