Land Cover Mapping with Convolutional Neural Networks Using Sentinel-2 Images: Case Study of Rome

Cecili, Giulia; Fioravante, Paolo De; Dichicco, Pasquale; Congedo, Luca; Marchetti, Marco; Munafò, Michele

doi:10.3390/land12040879

Cited by 14 publications

(2 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Within the CNN algorithm, ResNet50, a variant of ResNet, holds significance (Cecili et al, 2023). In the domain of land type recognition, ResNet-50 offers distinct advantages, characterized by its depth, residual connections, and training on extensive image datasets.…”

Section: B Deep Learning and Its Application In Land Type Identificat...mentioning

confidence: 99%

Clustering Analysis of Integrated Rural Land for Three Industries Using Deep Learning and Artificial Intelligence

Huang,

Xia,

Zhang

2023

IEEE Access

View full text Add to dashboard Cite

This study employs deep learning and artificial intelligence (AI) clustering analysis techniques to evaluate the suitability of integrated rural land for three industries. Diverse datasets pertaining to rural development, encompassing land use, agricultural production, and rural tourism, are gathered and harmoniously amalgamated. An innovative land suitability assessment model, merging ResNet-50 with the k-means algorithm, is devised. Specifically, ResNet-50 is harnessed for the classification and recognition of rural land-use images, thus deriving feature vectors for each sample. These feature vectors are subsequently fed into the k-means algorithm to cluster samples with akin land-use patterns. The ensuing examination of land use composition within each cluster facilitates the evaluation of rural land's suitability for three-industry integration. Experimental scrutiny discloses that this study achieves an accuracy rate of 88.3% in rural landuse classification and recognition, outperforming alternative algorithms by at least 3.1%. Furthermore, it yields an average intersection over union (IoU) of 67.29%. Remarkably, the k-means algorithm exhibits superior clustering outcomes. Consequently, the model introduces herein demonstrated substantial enhancements in rural land-use classification and recognition accuracy, average IoU, and clustering performance. It offers an innovative tool for policymakers to advance rural industry integration, fostering economic diversification. Additionally, this model aids decision-makers in identifying prospective opportunities and challenges, thus facilitating the formulation of forward-thinking and viable rural development strategies.

show abstract

Section: B Deep Learning and Its Application In Land Type Identificat...mentioning

confidence: 99%

Clustering Analysis of Integrated Rural Land for Three Industries Using Deep Learning and Artificial Intelligence

Huang,

Xia,

Zhang

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The role of vegetation in maintaining ecological resilience is crucial (Hugo Carrao et al n.d.;Cecili et al 2023;Alam et al 2019). Although vegetation monitoring alone is insufficient to interpret land cover (LC) resilience comprehensively and still needs to be combined with other information, such as climate data, soil data, and land use data, to provide a more holistic understanding of the overall ecosystem condition.…”

Section: Introductionmentioning

confidence: 99%

Measuring climate action readiness in maintaining ecological resilience using satellite imagery and field research in Garang Watershed, Central Java, Indonesia

et al. 2023

View full text Add to dashboard Cite

Abstract. Sudarmanto B, Suranto S, Suntoro S, Sutrisno J. 2023. Measuring climate action readiness in maintaining ecological resilience using satellite imagery and field research in Garang Watershed, Central Java, Indonesia. Biodiversitas 24: 2958-2974. The long-term viability of vegetation as a representation of land cover in a watershed is critical. However, more work is needed to develop vegetation management in the form of a climate action model that considers the existence of ecological and social values as a unified system, particularly in times of climate change. Moran's Index measurements and statistical correlation analysis were employed in this study to quantify geographical patterns. These measurements provide real-world judgment in developing aggressive climate response scenarios. Ecological values were derived from shifting vegetation trend indices due to mutual interaction between living beings that build a life cycle in harmony with the environment. Meanwhile, social values are determined by assessing individual internal factors such as attitudes, knowledge, and responses and external factors represented by local government institutions. The findings reveal that the distribution of residents and residential areas is dispersed. With a high confidence level, a linear index declines with R2 = 0.5872 for inhabitants and R2 = 0.9171 for residential areas. In the dry season, there is a significant relationship between the spatial pattern of vegetation indices and the inhabitant's index. The community's knowledge and attitudes considerably impact changes in vegetation indices, particularly during the rainy season, with R2 = 0.207 for SAVI and 0.232 for NDVI. Community readiness values, which elaborate on knowledge, attitudes, responses, and the role of external institutions, show that community readiness in the upstream area of the watershed, specifically in the Kendal District, is in the best position, with a value of 6.627976. On the contrary, the Semarang District, the upstream area, has the lowest value of 4.257092.

show abstract

ISPRA Land and Soil Monitoring, Mapping, and Assessment Activities

Munafò,

De Fioravante,

Cimini

et al. 2024

Soil Science in Italy

View full text Add to dashboard Cite

Land Cover Mapping with Convolutional Neural Networks Using Sentinel-2 Images: Case Study of Rome

Cited by 14 publications

References 79 publications

Clustering Analysis of Integrated Rural Land for Three Industries Using Deep Learning and Artificial Intelligence

Clustering Analysis of Integrated Rural Land for Three Industries Using Deep Learning and Artificial Intelligence

Measuring climate action readiness in maintaining ecological resilience using satellite imagery and field research in Garang Watershed, Central Java, Indonesia

ISPRA Land and Soil Monitoring, Mapping, and Assessment Activities

Contact Info

Product

Resources

About