Land Consumption Mapping with Convolutional Neural Network: Case Study in Italy

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

doi:10.3390/land11111919

Cited by 7 publications

(7 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning (DL) techniques have recently been widely incorporated for the classification of remote sensing images, but fewer research have used them for land consumption (LC) i.e the land transformation process which results into the loss of agricultural, natural and semi-natural areas due to the construction of new buildings, the expansion of cities, and the infrastructure in the city [18], [19]. In this study, multi-temporal Landsat images were acquired for the years 1990, 2000, 2013 and 2018.…”

Section: Methodsmentioning

confidence: 99%

Study on Spatial-Temporal Urban Growth and Land Consumption Patterns of Thimphu, Bhutan Using Multi-Temporal Satellite Images

Chhetri

2023

JAETM

View full text Add to dashboard Cite

Like many other countries, Bhutan is also experiencing rapid trend of urban expansion mainly due to out-migration from rural to urban areas particularly in capital city, Thimphu. This study focuses on the dynamics of urban expansion, evaluating urban growth and land consumption pattern of Thimphu, using multi-temporal Landsat images during the year 1990-2018. The main aim of the study is to perform supervised classification to classify built-up area, green area, bare-land and others (water bodies, agricultural lands, etc…) and to perform a change analysis from the viewpoint of increasing the built-up areas (man-made structures) and decreasing in green and open spaces. Moreover, the study also highlights how has the land consumption pattern of the region changed over the years. The findings of the study confirmed that the Thimphu city has its built-up areas increased during 1990-2018 with net growth of 4.63 km2 (106.19%). The urban area was 4.36 km2 in 1990, 5.80 km2 in 2000 (33.03% growth), which increased to 7.24 km2 in 2013 (24.83% growth) and 8.99 km2 (24.17% growth) in 2018. The study also showed that there is decrease in land consumption between 1990-2018. In 1990, land consumption was 155.65 m2 per person which decreased to 78.48 m2 per person in 2018. This decrease in land consumption indicate that the city is experiencing increased densification between the years 1990-2018. The classifier performance evaluation was done using overall accuracy and kappa coefficient. The classification produced an overall accuracies ranging between 78.74% to 90.46 % and overall kappa statistics between 0.72 to 0.87 for all years indicating classification accuracy of moderate to substantial accuracy.

show abstract

Section: Methodsmentioning

confidence: 99%

Study on Spatial-Temporal Urban Growth and Land Consumption Patterns of Thimphu, Bhutan Using Multi-Temporal Satellite Images

Chhetri

2023

JAETM

View full text Add to dashboard Cite

show abstract

“…A belvíz lehatárolására különböző módszerek (indexek, osztályozások, tradicionális gépi tanulás, mély neurális hálózatok) állnak rendelkezésre. A neurális hálózatok az utóbbi években, főleg a mély neurális hálózatok, ezeken belül a LeCun és munkatársai (1990) által megalkotott konvolúciós neurális hálózat (CNN), egyre nagyobb térnyerése figyelhető meg a földtudományi alkalmazásokban (LeCun et al 1990, Giulia et al 2023, Yichen et al 2022, Sánchez et al 2022. Korábbi vizsgálataink során nyolc módszert alkalmaztunk a belvíz detektálására, amelyek közül a CNN bizonyult a legpontosabbnak a vizsgált Sentinel-2-es, nagy felbontású, multispektrális műholdképeken (Kajári-Van Leeuwen 2021).…”

Section: Bevezetésunclassified

Sentinel-1 és Sentinel-2 felvételek belvízveszélyeztetettségi idősoros elemzése konvolúciós neurális hálózatokkal

Kajári,

Leeuwen

2024

View full text Add to dashboard Cite

Presently, climate change is expected to cause extreme weather more often, which may result in increasingly frequent and widespread inundations. Shallow floods, also defined as inland excess water, are complex phenomena, which makes it very difficult to initiate preventive action and to identify areas at risk. It is therefore important to develop a "near-continuous" monitoring system based on images from the Sentinel constellation of active and passive satellites, available from the European Space Agency (ESA), covering large areas and with sufficient spatial resolution. We used convolutional neural networks (CNNs -Convolutional Neural Networks) to delineate water surfaces, which were temporally interpolated to create a frequency map over the whole year by filling temporal and spatial gaps in the time series. In the 1600 km 2 study area, we delineated 17,80 km 2 of permanent water surface, and 5,64 km 2 of highly, 3,70 km 2 of moderately and 7,79 km 2 of land slightly vulnerable to inland excess water.

show abstract

“…There are a variety of CNN architectures that can be used for LC classification, such as the VGGNet [48], AlexNet [49], ResNet [50], DenseNet [51] and U-Net [52]. Several of these algorithms have been used successfully on RGB [53,54], multispectral [55,56] and hyperspectral data [57][58][59], and the state of the art reveals many publications regarding classification of not freely available high-resolution images [54,60,61]. However, various DL methods were recently utilized to generate LU and LC maps using free data, which are receiving particular attention because their high temporal resolution allows for significant cost savings in high-frequency monitoring [62][63][64], e.g., Hu et al [65] used Landsat-8 images for wetland cover classification with a VGG, Di Pilato et al [66] focused their study on the detection of changes in urban areas using a CNN on Sentinel-2 images, Mirmazloumi et al [12] developed a workflow to generate a LULC map of Europe using Sentinel and Landsat-8 images.…”

Section: Introduction Backgroundmentioning

confidence: 99%

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

Cecili

Fioravante

Dichicco

et al. 2023

Land

Self Cite

View full text Add to dashboard Cite

Land cover monitoring is crucial to understand land transformations at a global, regional and local level, and the development of innovative methodologies is necessary in order to define appropriate policies and land management practices. Deep learning techniques have recently been demonstrated as a useful method for land cover mapping through the classification of remote sensing imagery. This research aims to test and compare the predictive models created using the convolutional neural networks (CNNs) VGG16, DenseNet121 and ResNet50 on multitemporal and single-date Sentinel-2 satellite data. The most promising model was the VGG16 both with single-date and multi-temporal images, which reach an overall accuracy of 71% and which was used to produce an automatically generated EAGLE-compliant land cover map of Rome for 2019. The methodology is part of the land mapping activities of ISPRA and exploits its main products as input and support data. In this sense, it is a first attempt to develop a high-update-frequency land cover classification tool for dynamic areas to be integrated in the framework of the ISPRA monitoring activities for the Italian territory.

show abstract

Land Consumption Mapping with Convolutional Neural Network: Case Study in Italy

Cited by 7 publications

References 51 publications

Study on Spatial-Temporal Urban Growth and Land Consumption Patterns of Thimphu, Bhutan Using Multi-Temporal Satellite Images

Study on Spatial-Temporal Urban Growth and Land Consumption Patterns of Thimphu, Bhutan Using Multi-Temporal Satellite Images

Sentinel-1 és Sentinel-2 felvételek belvízveszélyeztetettségi idősoros elemzése konvolúciós neurális hálózatokkal

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

Contact Info

Product

Resources

About