Uncovering Vegetation Changes in the Urban–Rural Interface through Semi-Automatic Methods

Barbosa, Bruno; Rocha, Jorge; Costa, Hugo; Caetano, Mário

doi:10.3390/app12052294

Cited by 3 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The imperviousness HRL represents the spatial distribution of artificially sealed areas, including the degree of soil sealing per unit area. The level of soil sealing (degree of imperviousness from 1 to 100) is produced using a semi-automated classification based on calibrated normalized difference vegetation index [51][52][53]. The forest density dataset was then used to classify the unbuilt land.…”

Section: Land Use Land Covermentioning

confidence: 99%

Adapting Cities to Pluvial Flooding: The Case of Izmir (Türkiye)

et al. 2022

View full text Add to dashboard Cite

In the coming decades, climate change will be one of the most significant challenges for urban areas. The quantity, duration and intensity of events, such as flash rains and heat waves, will increase the vulnerability of urban regions while exposing citizens to potentially dangerous conditions. According to the current literature, mainstreaming resilience in urban planning means designing rules that strengthen urban systems’ adaptive and self-regulating functions by reducing their vulnerability. In this work, we aimed to build knowledge for the application of the sponge district concept to Izmir (Türkiye), one of Europe’s most vulnerable areas to pluvial flooding. To do this, we first analyzed the runoff in each urban sub-watershed, then employed a composite index to determine potential areas of intervention for nature-based solutions. Results show that 10% of Izmir’s urban areas are extremely vulnerable to cloudbursts, which means that 40% of the urban population is exposed to this phenomenon. Moreover, the runoff calculation in the sub-watershed demonstrated that the potential flood volume is underestimated, especially in the upslope areas. The results can be used as a template to suggest a stepwise approach to mainstream the resilience of densely-inhabited coastal urban catchments.

show abstract

Section: Land Use Land Covermentioning

confidence: 99%

Adapting Cities to Pluvial Flooding: The Case of Izmir (Türkiye)

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Few studies investigate its operationalization, and there is a high degree of uncertainty about how the system should be measured empirically and how it should be designed to effectively perform nature conservation [31], thus, there is a fundamental need for a standardized measure of the impact by systematic monitoring. Regarding the second aspect, significant differences arise within the scope and kind of indicators that are used to measure the impacts of land-use changes [35]. Soil sealing, tree cover density, habitat quality, carbon sequestration, nutrient retention, water yield, and many other biophysical datasets can be employed to measure the impacts of human-induced land alteration [36].…”

Section: Introductionmentioning

confidence: 99%

“…Considering vegetation by defining different NDVI threshold values such as 10%, 15% or 20% can be considered relevant for short-time monitoring, while defining NDVI threshold values of 25% to 50% can be considered large steps for longer time interval observations [33]. According to this approach, it is commonly used to detect statistically significant differences between NDVI values in small catchment sites while employing standard deviation (zscores) and probability values (p-scores) at certain confidence levels in small spatial radius (500 m or less) [35].…”

Section: Introductionmentioning

confidence: 99%

Monitoring Soil Degradation Processes for Ecological Compensation in the Izmir Institute of Technology Campus (Turkey)

Salata

Couch

2022

Eng

View full text Add to dashboard Cite

Monitoring changing environmental conditions for short-term periods is a key aspect of adaptive urban planning. Unfortunately, the official environmental datasets are often produced at too large time intervals, and sometimes the speed of urban transformation requires real-time monitoring data. In this work we employed ESRI ArcGIS (ver. 10.8.1) to process two normalized difference vegetation indices for the campus area of the Izmir Institute of Technology (Turkey). The area of this campus constitutes an optimal site for testing whether alterations to the soil due to excavation and new construction can be monitored in small areas of land. We downloaded two different Sentinel acquisitions from the Copernicus ONDA DİAS platform: one taken on 28 March 2021 and the second taken on 13 March 2022. We processed the images while elaborating the normalized difference vegetation index for both years and compared them. Results demonstrate that all major and minor soil degradations on the campus during the intervening year were detected and empirically quantified in terms of NDVİ reduction (abrupt changes). These findings confirm that detailed seasonal environmental monitoring of every part of the world is now possible using semi-automatic procedures to process original Sentinel data and recommend site-specific ecological compensation measures.

show abstract

A Study of Forest Phenology Prediction Based on GRU Models

Guan

Zhu

2023

Applied Sciences

View full text Add to dashboard Cite

Investigating forest phenology prediction is a key parameter for assessing the relationship between climate and environmental changes. Traditional machine learning models are not good at capturing long-term dependencies due to the problem of vanishing gradients. In contrast, the Gated Recurrent Unit (GRU) can effectively address the problem of vanishing gradients and allow the neural network to capture longer-range dependencies. In this study, an optical camera was used as experimental equipment to obtain forest images. The absolute greenness index (GEI) data of the region of interest (ROI) in the images were calculated to fit the seasonal variation curve of forest phenology. The GRU neural network model was introduced to train and analyze the GEI data, and the performance of the GRU neural network was evaluated using the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) methods. Finally, the model was used to predict the trend of GEI data for the next 60 days. The results showed that: (1) In terms of training and predicting forest phenology, the GRU model was validated using histograms and autocorrelation graphs, which indicated that the distribution of predicted data was consistent with the trend of actual data, the GRU model data was feasible, and the model was stable. (2) The MSE values of the GRU model at rain-fed-CK (preset point 1), sufficient drip irrigation-DIFI (preset point 3), and sufficient furrow irrigation-BIFI (preset point 5) were 9.055 × 10−5, 12.91 × 10−5, and 8.241 × 10−5, respectively. The RMSE values were 9.516 × 10−3, 11.36 × 10−3, and 7.313 × 10−3, respectively. The MAE values were 7.174 × 10−3, 8.241 × 10−3, and 5.351 × 10−3, respectively. These results indicate that the overall performance of the GRU model was good. (3) The predicted GEI data for the next 60 days showed a trend consistent with actual changes in GEI data, as demonstrated by the GRU model. The GRU model has become the preferred method for phenological prediction due to its simple internal structure and relatively short training time. Results show that the GRU model can achieve forest phenological change prediction and can reveal in-depth insights into future forest growth and climate change, providing a theoretical basis for the application of forest phenological prediction.

show abstract

Uncovering Vegetation Changes in the Urban–Rural Interface through Semi-Automatic Methods

Cited by 3 publications

References 37 publications

Adapting Cities to Pluvial Flooding: The Case of Izmir (Türkiye)

Adapting Cities to Pluvial Flooding: The Case of Izmir (Türkiye)

Monitoring Soil Degradation Processes for Ecological Compensation in the Izmir Institute of Technology Campus (Turkey)

A Study of Forest Phenology Prediction Based on GRU Models

Contact Info

Product

Resources

About