A framework for separating natural and anthropogenic contributions to evapotranspiration of human-managed land covers in watersheds based on machine learning

Zeng, Hongwei; Elnashar, Abdelrazek; Wu, Bingfang; Zhang, Miao; Zhu, Weiwei; Tian, Fuyou; Ma, Zonghan

doi:10.1016/j.scitotenv.2022.153726

Cited by 10 publications

(4 citation statements)

References 91 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All these variabilities contributed to causing the model performance uncertainties. Overall, a novel and robust AutoML approach has been developed achieving satisfactory accuracy and could be applied in other environments to predict smallholder yield using different data sources, rather than using the traditional machine learning approaches [80][81][82]. The work strengths could be summarized in developing a novel automatic machine learning library for fast, quick, and robust predictions using the maximum number of models include the ensemble model.…”

Section: Discussionmentioning

confidence: 99%

Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset

Kheir,

Govind,

Nangia

et al. 2024

Environ. Res. Commun.

Self Cite

View full text Add to dashboard Cite

Estimating smallholder crop yields robustly and timely is crucial for improving agronomic practices, determining yield gaps, guiding investment, and policymaking to ensure food security. However, there is poor estimation of yield for most smallholders due to lack of technology, and field scale data, particularly in Egypt. Automated machine learning (AutoML) can be used to automate the machine learning workflow, including automatic training and optimization of multiple models within a user-specified time frame, but it has less attention so far. Here, we combined extensive field survey yield across wheat cultivated area in Egypt with diverse dataset of remote sensing, soil, and weather to predict field-level wheat yield using 22 ML models in AutoML. The models showed robust accuracies for yield predictions, recording Willmott degree of agreement, (d > 0.80) with higher accuracy when super learner (stacked ensemble) was used (R2 = 0.51, d = 0.82). The trained AutoML was deployed to predict yield using remote sensing (RS) vegetative indices (VIs), demonstrating a good correlation with actual yield (R2 = 0.7). This is very important since it is considered a low-cost tool and could be used to explore early yield predictions. Since climate change has negative impacts on agricultural production and food security with some uncertainties, AutoML was deployed to predict wheat yield under recent climate scenarios from the Coupled Model Intercomparison Project Phase 6 (CMIP6). These scenarios included single downscaled General Circulation Model (GCM) as CanESM5 and two shared socioeconomic pathways (SSPs) as SSP2-4.5and SSP5-8.5during the mid-term period (2050). The stacked ensemble model displayed declines in yield of 21 % and 5 % under SSP5-8.5 and SSP2-4.5 respectively during mid-century, with higher. The developed approach could be used as a rapid, accurate and low-cost method to predict yield for stakeholder farms all over the world where ground data is scarce.

show abstract

Section: Discussionmentioning

confidence: 99%

Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset

Kheir,

Govind,

Nangia

et al. 2024

Environ. Res. Commun.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The third main topic that CCHSR focuses on consists of the utilising Novel Technologies, such as Machine Learning. Machine learning (ML) and cloud computing have experienced substantial growth in recent years and have found wide-ranging applications in areas such as building energy simulation [70], urban land cover classification, water resource forecasting [71], and beyond. For instance, Mazhar used machine learning techniques to identify and analyse vegetation and urbanisation in Pakistan from 2013 to 2021, thereby illuminating extant trends in land use and human settlement suitability [72].…”

Section: Summary Of Key Issuesmentioning

confidence: 99%

Study on the Progress in Climate-Change-Oriented Human Settlement Research

Yao

Yang

et al. 2023

Sustainability

View full text Add to dashboard Cite

Since the 20th century, the escalating impact of climate risks has led to a heightened global focus on climate-change-oriented human settlement research (hereafter referred to as CCHSR). This paper presents an econometric analysis of 6830 research papers published from 1975 to 2023 (first two months) to investigate the characteristics, key issues, and research trends in CCHSR, to provide valuable insights and recommendations for future research. We used CiteSpace, bibliometric software that constructs a knowledge-mapping analysis of annual publication volume, source publications, and country distribution; this study examines the characteristics of the literature sources in CCHSR. It also explores the literature distribution through an analysis of co-citation and collaboration. The study identifies the key topics of current research through a keyword clustering analysis, including extreme climate risk response, environmental safety and sustainability enhancement, and machine learning technology application. The study identifies three research trends for future investigations by analysing keyword emergence, including climate risk governance implementation, artificial intelligence technology application, and settlement security and resilience enhancement. Finally, the study presents recommendations for priority CCHSR in three areas: theoretical system development, mechanism strategy design, and technology implementation.

show abstract

“…The sense of place is a kind of special relationship between people and land formed by long-term interaction between people and the land. It is based on the subjectivity of human local experience [20]. In a certain scope, through people's experience of long-term living and activities, the emotional attachment and identity for a particular place are generated [21], which emphasizes people's sense of belonging to a place and the sense of "home".…”

Section: Residents' Sense Of Place In Suburban Industrial Development...mentioning

confidence: 99%

Sustainability of Suburban Industrial Development through Place Attachment

Long

Chuang

et al. 2022

Civ Eng J

View full text Add to dashboard Cite

This research uses urban space reconstruction as the entry point, discussing the characteristics of residents’ sense of place in Lingang new town, Shanghai, based on the method of factor analysis to divide the sense of place into place attachment, place identity, and place dependence. On the whole, residents’ sense of place in Lingang new town is at a common level, and the comprehensive score of residents’ sense of place in Lingang new town is "more than half". Meanwhile, place attachment is the highest, place dependence is the lowest, and place identity is in the middle. Therefore, the sense of place mainly depends on place attachment. Using an independent T test and variance analysis to explore the characteristics of the sense of place, this paper has found that age, income level, education level, household registration, and migration patterns have significantly different influences on the three dimensions of the sense of place. There is no difference in gender and the type of occupation, whether they are working in Lingang New Town or not. The research on the sense of place in suburban industrial development zones presents a new perspective for solving the social space problems in the development zone. Finally, this research suggests improving the construction of public facilities, paying more attention to youth groups’ sense of place, and enhancing the sense of belonging to the highly educated groups and high-income groups, as well as strengthening innovation and entrepreneurship cooperation between the new town and the main city. Doi: 10.28991/CEJ-2022-08-07-014 Full Text: PDF

show abstract

A framework for separating natural and anthropogenic contributions to evapotranspiration of human-managed land covers in watersheds based on machine learning

Cited by 10 publications

References 91 publications

Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset

Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset

Study on the Progress in Climate-Change-Oriented Human Settlement Research

Sustainability of Suburban Industrial Development through Place Attachment

Contact Info

Product

Resources

About