東華大學圖書館 |

Fusion of In-Situ and Remote Sensing Data With Machine Learning Toward Global Water and Food Security Monitoring /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Fusion of In-Situ and Remote Sensing Data With Machine Learning Toward Global Water and Food Security Monitoring // Katie Fankhauser.
Author:	Fankhauser, Katie,
Description:	1 electronic resource (140 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-03, Section: A.
Contained By:	Dissertations Abstracts International86-03A.
Subject:	Environmental engineering. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31485868
ISBN:	9798384048817

Fusion of In-Situ and Remote Sensing Data With Machine Learning Toward Global Water and Food Security Monitoring /
Fankhauser, Katie,

Fusion of In-Situ and Remote Sensing Data With Machine Learning Toward Global Water and Food Security Monitoring /Katie Fankhauser. - 1 electronic resource (140 pages)

Source: Dissertations Abstracts International, Volume: 86-03, Section: A.

Water and food insecurity are two of the most formidable challenges facing the world today: an estimated two billion people (26%) are without safe drinking water and four billion people (50%) contend with water scarcity for at least part of the year while two and a half billion people (30%) regularly experience moderate to severe food insecurity. The United Nations Sustainable Development Goals (SDGs) are designed to promote and monitor progress across several dimensions of economic, social, and environmental sustainability, including water and food security. Unfortunately, global progress towards these targets ahead of the 2030 deadline is severely off track. Moreover, global estimates tend to obscure inequalities between and within countries and low- and middle-income populations in sub-Saharan Africa are faring the worst due to the impact of climate change and greater socioeconomic vulnerability. An urgent call for action and policy solutions is warranted to identify what needs to be done, for and with whom. However, current monitoring schemes for many SDG targets, including those related to water and food security, are not up to the challenge and exhibit problems of data latency and coarse resolution at odds with the type of data and decision tools that would enable targeted solutions. Many researchers, policymakers, and practitioners are advocating for the localization of the SDGs and programmatic monitoring to realize real progress. Given data limitations in most developing contexts, satellite remote sensing and the use of machine learning tools may be one of the only cost-effective means of providing high-resolution, high frequency data that is uniform, collected in near-real time, and available across all geographies. The data fusion of existing in-situ data and satellite-derived observations, enabled by machine learning, complements ongoing monitoring efforts and advances the localization of monitoring.This dissertation presents how remote sensing, in-situ data, and machine learning can be assimilated to produce novel insights in service of localized monitoring and evidence-based targeting to address water and food insecurity in the arid and semi-arid lands (ASALs) of Kenya and Rwanda.In the Kenyan ASALs, population-based groundwater use and demand at 5 km resolution was predicted during dry season months for years 2017-2021 with in-season accuracy of 70-76% and forecasted accuracy of 68-75%. This tool assimilated both in-situ water pumping and remote sensing data and presented the first operational spatially explicit sub-seasonal to seasonal (S2S) maps of groundwater use in the literature. Knowledge of historical and forecasted groundwater use is designed to improve decision making and resource allocation for drought early warning and contribute to monitoring of indicators for SDG 6 related to water access and use by pastoralists.In Rwanda, wall-to-wall time series of maize area and yield at 10 m resolution and for 10 maize-growing seasons from 2019-2023 were developed to study the agricultural productivity of smallholders. Informed by in-situ crop cutting data, maize was classified with 83% accuracy and mean district-level yields had a root mean square error (RMSE) of 370 kg/ha (27%) against national estimates. This dataset enabled the evaluation of village-level response to a rural transportation project and the monitoring of Rwanda's recent growth in agricultural productivity as part of SDG 2 to achieve food security. While national progress is off track to double maize yields by 2030, this growth is unequal across villages and producers, and, depending on policy priorities, there are several scenarios for meeting national goals, bringing up the lowest yielding farmers, or both within the next six years.High-resolution data, enabled by machine learning and in-situ data, identified previously unmeasured spatial and temporal variation in indicators of water and food insecurity in these two contexts. It is likely that inequalities and inconsistent progress in attainment of the SDGs would be found for many other regions and SDG indicators at high-resolution. Highly differentiated and targeted policies and programs can accelerate progress and reduce inequalities efficiently. Thus, the localization of monitoring may be one necessary condition to achieve the SDGs fully in the short time remaining before 2030.

English

ISBN: 9798384048817Subjects--Topical Terms:

548583
Environmental engineering.
Subjects--Index Terms:

In-situ data

Fusion of In-Situ and Remote Sensing Data With Machine Learning Toward Global Water and Food Security Monitoring /
LDR:05970nmm a22004573i 4500 001 2434467
005 20250912102023.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798384048817
035 $a (MiAaPQD)AAI31485868
035 $a AAI31485868
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Fankhauser, Katie, $e author. $0 (orcid)0000-0003-2381-7796 $3 3824459
245 1 0 $a Fusion of In-Situ and Remote Sensing Data With Machine Learning Toward Global Water and Food Security Monitoring / $c Katie Fankhauser.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (140 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: 86-03, Section: A.
500 $a Advisors: Thomas, Evan Committee members: Mehrabi, Zia; Monteleoni, Claire; Salvinelli, Carlo; Senay, Gabriel.
502 $b Ph.D. $c University of Colorado at Boulder $d 2024.
520 $a Water and food insecurity are two of the most formidable challenges facing the world today: an estimated two billion people (26%) are without safe drinking water and four billion people (50%) contend with water scarcity for at least part of the year while two and a half billion people (30%) regularly experience moderate to severe food insecurity. The United Nations Sustainable Development Goals (SDGs) are designed to promote and monitor progress across several dimensions of economic, social, and environmental sustainability, including water and food security. Unfortunately, global progress towards these targets ahead of the 2030 deadline is severely off track. Moreover, global estimates tend to obscure inequalities between and within countries and low- and middle-income populations in sub-Saharan Africa are faring the worst due to the impact of climate change and greater socioeconomic vulnerability. An urgent call for action and policy solutions is warranted to identify what needs to be done, for and with whom. However, current monitoring schemes for many SDG targets, including those related to water and food security, are not up to the challenge and exhibit problems of data latency and coarse resolution at odds with the type of data and decision tools that would enable targeted solutions. Many researchers, policymakers, and practitioners are advocating for the localization of the SDGs and programmatic monitoring to realize real progress. Given data limitations in most developing contexts, satellite remote sensing and the use of machine learning tools may be one of the only cost-effective means of providing high-resolution, high frequency data that is uniform, collected in near-real time, and available across all geographies. The data fusion of existing in-situ data and satellite-derived observations, enabled by machine learning, complements ongoing monitoring efforts and advances the localization of monitoring.This dissertation presents how remote sensing, in-situ data, and machine learning can be assimilated to produce novel insights in service of localized monitoring and evidence-based targeting to address water and food insecurity in the arid and semi-arid lands (ASALs) of Kenya and Rwanda.In the Kenyan ASALs, population-based groundwater use and demand at 5 km resolution was predicted during dry season months for years 2017-2021 with in-season accuracy of 70-76% and forecasted accuracy of 68-75%. This tool assimilated both in-situ water pumping and remote sensing data and presented the first operational spatially explicit sub-seasonal to seasonal (S2S) maps of groundwater use in the literature. Knowledge of historical and forecasted groundwater use is designed to improve decision making and resource allocation for drought early warning and contribute to monitoring of indicators for SDG 6 related to water access and use by pastoralists.In Rwanda, wall-to-wall time series of maize area and yield at 10 m resolution and for 10 maize-growing seasons from 2019-2023 were developed to study the agricultural productivity of smallholders. Informed by in-situ crop cutting data, maize was classified with 83% accuracy and mean district-level yields had a root mean square error (RMSE) of 370 kg/ha (27%) against national estimates. This dataset enabled the evaluation of village-level response to a rural transportation project and the monitoring of Rwanda's recent growth in agricultural productivity as part of SDG 2 to achieve food security. While national progress is off track to double maize yields by 2030, this growth is unequal across villages and producers, and, depending on policy priorities, there are several scenarios for meeting national goals, bringing up the lowest yielding farmers, or both within the next six years.High-resolution data, enabled by machine learning and in-situ data, identified previously unmeasured spatial and temporal variation in indicators of water and food insecurity in these two contexts. It is likely that inequalities and inconsistent progress in attainment of the SDGs would be found for many other regions and SDG indicators at high-resolution. Highly differentiated and targeted policies and programs can accelerate progress and reduce inequalities efficiently. Thus, the localization of monitoring may be one necessary condition to achieve the SDGs fully in the short time remaining before 2030.
546 $a English
590 $a School code: 0051
650 4 $a Environmental engineering. $3 548583
650 4 $a Computer engineering. $3 621879
650 4 $a Remote sensing. $3 535394
650 4 $a Climate change. $2 bicssc $3 2079509
650 4 $a Sustainability. $3 1029978
653 $a In-situ data
653 $a Machine learning
653 $a Sustainable Development Goals
653 $a Water and food security
653 $a Middle-income populations
690 $a 0775
690 $a 0640
690 $a 0464
690 $a 0404
690 $a 0799
710 2 $a University of Colorado at Boulder. $b Civil, Environmental, and Architectural Engineering. $e degree granting institution. $3 3765764
720 1 $a Thomas, Evan $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-03A.
790 $a 0051
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31485868