Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
High-resolution sensors onboard satellites are generally reputed for rapidly producing land-use/land-cover (LULC) maps with improved spatial detail. However, such maps are subject to uncertainties due to several factors, including the training sample size. We investigated the effects of different training sample sizes (from 1000 to 12,000 pixels) on LULC classification accuracy using the random forest (RF) classifier. Then, we analyzed classification uncertainties by determining the median and the interquartile range (IQR) of the overall accuracy (OA) values through repeated k-fold cross-validation. Results showed that increasing training pixels significantly improved OA while minimizing model uncertainty. Specifically, larger training samples, ranging from 9000 to 12,000 pixels, exhibited narrower IQRs than smaller samples (1000–2000 pixels). Furthermore, there was a significant variation (Chi2 = 85.073; df = 11; p < 0.001) and a significant trend (J-T = 4641, p < 0.001) in OA values across various training sample sizes. Although larger training samples generally yielded high accuracies, this trend was not always consistent, as the lowest accuracy did not necessarily correspond to the smallest training sample. Nevertheless, models using 9000–11,000 pixels were effective (OA > 96%) and provided an accurate visual representation of LULC. Our findings emphasize the importance of selecting an appropriate training sample size to reduce uncertainties in high-resolution LULC classification.
High-resolution sensors onboard satellites are generally reputed for rapidly producing land-use/land-cover (LULC) maps with improved spatial detail. However, such maps are subject to uncertainties due to several factors, including the training sample size. We investigated the effects of different training sample sizes (from 1000 to 12,000 pixels) on LULC classification accuracy using the random forest (RF) classifier. Then, we analyzed classification uncertainties by determining the median and the interquartile range (IQR) of the overall accuracy (OA) values through repeated k-fold cross-validation. Results showed that increasing training pixels significantly improved OA while minimizing model uncertainty. Specifically, larger training samples, ranging from 9000 to 12,000 pixels, exhibited narrower IQRs than smaller samples (1000–2000 pixels). Furthermore, there was a significant variation (Chi2 = 85.073; df = 11; p < 0.001) and a significant trend (J-T = 4641, p < 0.001) in OA values across various training sample sizes. Although larger training samples generally yielded high accuracies, this trend was not always consistent, as the lowest accuracy did not necessarily correspond to the smallest training sample. Nevertheless, models using 9000–11,000 pixels were effective (OA > 96%) and provided an accurate visual representation of LULC. Our findings emphasize the importance of selecting an appropriate training sample size to reduce uncertainties in high-resolution LULC classification.
Sub-Saharan Africa (SSA) is undergoing rapid urbanization, yet research comparing urban expansion and agricultural land loss in peri-urban areas is scarce. This study utilizes multi-temporal Landsat imagery to examine the impact of urban growth on agricultural land and fragile ecosystems in Kampala (a mega city) and Mbarara (a regional urban center) in Uganda. We distinguish between random and systematic land-use and land-cover (LULC) transitions in the landscape. The results reveal substantial urban expansion. Kampala’s urban area surged from 7.14% in 1989 to 55.10% in 2015, while Mbarara increased from 6.37% in 2002 to 30.95% in 2016. Correspondingly, agricultural land decreased, from 48.02% to 16.69% in Kampala, and from 39.92% to 32.08% in Mbarara. Notably, a significant proportion of urban growth in both cities encroached upon agricultural land (66.7% in Kampala and 57.8% in Mbarara). The transition from agricultural to built-up areas accounted for 14.72% to 28.45% of the landscapes. Additionally, unsustainable practices led to the conversion of wetlands and forests to agricultural land, with approximately 13% of wetlands and 23% of Savannah and forests being converted between 2001 and 2015. These findings underscore the necessity of monitoring LULC changes for sustainable urban growth management, emphasizing the importance of preserving agricultural land and ecosystems to ensure present and future food security. This research contributes to the understanding of urbanization’s impact on peri-urban agricultural land and ecosystems in SSA, providing insights that are crucial for informed urban planning and policy formulation aimed at sustainable development in the region.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.