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

Leveraging Ground and Proximal Sensi...

Teshome, Fitsum,

Linked to FindBook

Google Book

Amazon

博客來

Leveraging Ground and Proximal Sensing, Crop Growth Models, and Artificial Intelligence to Simulate Soil Hydrologic Dynamics and Plant Responses From Irrigated Fields /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Leveraging Ground and Proximal Sensing, Crop Growth Models, and Artificial Intelligence to Simulate Soil Hydrologic Dynamics and Plant Responses From Irrigated Fields // Fitsum Teshome.
Author:	Teshome, Fitsum,
Description:	1 electronic resource (300 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-04, Section: B.
Contained By:	Dissertations Abstracts International86-04B.
Subject:	Agriculture. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31484135
ISBN:	9798384470618

Leveraging Ground and Proximal Sensing, Crop Growth Models, and Artificial Intelligence to Simulate Soil Hydrologic Dynamics and Plant Responses From Irrigated Fields /
Teshome, Fitsum,

Leveraging Ground and Proximal Sensing, Crop Growth Models, and Artificial Intelligence to Simulate Soil Hydrologic Dynamics and Plant Responses From Irrigated Fields /Fitsum Teshome. - 1 electronic resource (300 pages)

Source: Dissertations Abstracts International, Volume: 86-04, Section: B.

Recent advancements in proximal sensing, modeling, and artificial intelligence (AI) offer significant opportunities to closely monitor soil hydrologic (SH) dynamics and crop response to different irrigation levels. This study aimed to develop data-driven decision support tools to estimate and predict crop responses from variably irrigated sweet corn (SC) and green beans (GB) experimental plots. The study leveraged ground as well as above canopy infrared and unmanned aerial vehicle (UAV)-based thermal and multispectral sensors, crop growth models, and AI to simulate soil moisture (SM) and crop evapotranspiration (ETc) dynamics, physiological and phenological responses of SC and GB to different irrigation levels. Results showed that deficit irrigation strategies, reducing irrigation by up to 75% based on SM depletion, could be implemented in SC and GB fields without affecting yield, saving an average of 1,708 and 1,272 m3 ha-1 of water, respectively. The Decision Support System for Agrotechnology Transfer (DSSAT) model was developed for South Florida's specific soil conditions, and it simulated growth, yield, and SM dynamics with average MAE of 0.05 and 0.03 cm3 cm-3 for SC and GB, respectively. Machine learning (ML) algorithms and UAV-based imaging techniques were developed that predicted SC yield and yield components in response to different irrigation levels with an r2 of 0.99 and RMSE of 7 cm for plant height. These techniques provide timely and non-destructive information about crop phenological responses to water stress levels, which can inform irrigation management decisions. Furthermore, ML algorithms were developed to reliably estimate sub-hourly SM with average r2 and RMSE values of 0.85 and 0.02 cm3 cm-3 for SC and 0.83 and 0.02 cm3 cm-3 for GB. The ML algorithms were also effective in simulating daily ETc with average d-Stat and MAE of 0.9 and 0.6 mm day-1 for SC and 0.88 and 0.64 mm day-1 for GB. The study demonstrated that emerging technologies, such as ground and UAV-based sensors, simulation models, and AI, can be effectively leveraged to estimate field-scale SH and crop responses with greater accuracy. The models and ML algorithms developed in this research could be utilized to inform irrigation management decisions and optimize agricultural water management.

English

ISBN: 9798384470618Subjects--Topical Terms:

518588
Agriculture.
Subjects--Index Terms:

Crop evapotranspiration

Leveraging Ground and Proximal Sensing, Crop Growth Models, and Artificial Intelligence to Simulate Soil Hydrologic Dynamics and Plant Responses From Irrigated Fields /
LDR:03975nmm a22004693i 4500 001 2435736
005 20251029060338.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798384470618
035 $a (MiAaPQD)AAI31484135
035 $a AAI31484135
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Teshome, Fitsum, $e author. $3 3826145
245 1 0 $a Leveraging Ground and Proximal Sensing, Crop Growth Models, and Artificial Intelligence to Simulate Soil Hydrologic Dynamics and Plant Responses From Irrigated Fields / $c Fitsum Teshome.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (300 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: 86-04, Section: B.
500 $a Advisors: Bayabil, Haimanote K. Committee members: Ampatzidis, Ioannis; Schaffer, Bruce; Hoogenboom, Gerrit; Singh, Aditya.
502 $b Ph.D. $c University of Florida $d 2024.
520 $a Recent advancements in proximal sensing, modeling, and artificial intelligence (AI) offer significant opportunities to closely monitor soil hydrologic (SH) dynamics and crop response to different irrigation levels. This study aimed to develop data-driven decision support tools to estimate and predict crop responses from variably irrigated sweet corn (SC) and green beans (GB) experimental plots. The study leveraged ground as well as above canopy infrared and unmanned aerial vehicle (UAV)-based thermal and multispectral sensors, crop growth models, and AI to simulate soil moisture (SM) and crop evapotranspiration (ETc) dynamics, physiological and phenological responses of SC and GB to different irrigation levels. Results showed that deficit irrigation strategies, reducing irrigation by up to 75% based on SM depletion, could be implemented in SC and GB fields without affecting yield, saving an average of 1,708 and 1,272 m3 ha-1 of water, respectively. The Decision Support System for Agrotechnology Transfer (DSSAT) model was developed for South Florida's specific soil conditions, and it simulated growth, yield, and SM dynamics with average MAE of 0.05 and 0.03 cm3 cm-3 for SC and GB, respectively. Machine learning (ML) algorithms and UAV-based imaging techniques were developed that predicted SC yield and yield components in response to different irrigation levels with an r2 of 0.99 and RMSE of 7 cm for plant height. These techniques provide timely and non-destructive information about crop phenological responses to water stress levels, which can inform irrigation management decisions. Furthermore, ML algorithms were developed to reliably estimate sub-hourly SM with average r2 and RMSE values of 0.85 and 0.02 cm3 cm-3 for SC and 0.83 and 0.02 cm3 cm-3 for GB. The ML algorithms were also effective in simulating daily ETc with average d-Stat and MAE of 0.9 and 0.6 mm day-1 for SC and 0.88 and 0.64 mm day-1 for GB. The study demonstrated that emerging technologies, such as ground and UAV-based sensors, simulation models, and AI, can be effectively leveraged to estimate field-scale SH and crop responses with greater accuracy. The models and ML algorithms developed in this research could be utilized to inform irrigation management decisions and optimize agricultural water management.
546 $a English
590 $a School code: 0070
650 4 $a Agriculture. $3 518588
650 4 $a Agricultural engineering. $3 3168406
650 4 $a Soil sciences. $3 2122699
650 4 $a Hydrologic sciences. $3 3168407
650 4 $a Remote sensing. $3 535394
653 $a Crop evapotranspiration
653 $a Proximal sensing
653 $a Soil hydrologic dynamics
653 $a Soil moisture
653 $a Unmanned aerial vehicle
690 $a 0539
690 $a 0473
690 $a 0481
690 $a 0388
690 $a 0800
690 $a 0799
710 2 $a University of Florida. $b Agricultural and Biological Engineering. $e degree granting institution. $3 3826146
720 1 $a Bayabil, Haimanote K. $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-04B.
790 $a 0070
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31484135