A low-cost approach for soil moisture prediction using multi-sensor data and machine learning algorithm

The Science of The Total Environment, Journal Year: 2022, Volume and Issue: 833, P. 155066 - 155066

Published: April 7, 2022

Language: Английский

---

A novel intelligence approach based active and ensemble learning for agricultural soil organic carbon prediction using multispectral and SAR data fusion

The Science of The Total Environment, Journal Year: 2021, Volume and Issue: 804, P. 150187 - 150187

Published: Sept. 8, 2021

Language: Английский

---

Advances in Earth observation and machine learning for quantifying blue carbon

Earth-Science Reviews, Journal Year: 2023, Volume and Issue: 243, P. 104501 - 104501

Published: July 13, 2023

Blue carbon ecosystems (mangroves, seagrasses and saltmarshes) are highly productive coastal habitats, considered some of the most carbon-dense on earth. They an important nature-based solution for both climate change mitigation adaptation. Quantifying blue stocks assessing their dynamics at large scales through remote sensing remains challenging due to difficulties cloud coverage, spectral, spatial temporal limitations multispectral sensors speckle noise synthetic aperture radar (SAR). Recent advances in airborne space-borne SAR imagery Light Detection Ranging (LiDAR) data, sensor platforms such as unmanned aerial vehicles (UAVs), combined with novel machine learning techniques have offered different users a wide-range spatial, multi-temporal information quantifying from space. However, number challenges posed by various traits atmospheric correction, water penetration, column transparency issues environments, multi-dimensionality size LiDAR limitation training samples, backscattering mechanisms acquisition process. As result, existing methodologies face major accurately estimating using these datasets. In this context, emerging innovative artificial intelligence often required robustness reliability estimates, particularly those open-source software signal processing regression tasks. This review provides overview Earth Observation state-of-the-art deep that currently being used quantify above-ground carbon, below-ground soil mangroves, saltmarshes ecosystems. Some key future directions potential use data fusion advanced learning, metaheuristic optimisation also highlighted. summary, quantification approaches holds great contributing global efforts towards mitigating protecting

Language: Английский

---

A survey on the utilization of Superpixel image for clustering based image segmentation

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 82(23), P. 35493 - 35555

Published: March 8, 2023

Language: Английский

---

Technology and Data Fusion Methods to Enhance Site-Specific Crop Monitoring

Agronomy, Journal Year: 2022, Volume and Issue: 12(3), P. 555 - 555

Published: Feb. 23, 2022

Digital farming approach merges new technologies and sensor data to optimize the quality of crop monitoring in agriculture. The successful fusion technology is highly dependent on parameter collection, modeling adoption, integration being accurately implemented according specified needs farm. This technique has not yet been widely adopted due several challenges; however, our study here reviews current methods applications for fusing data. First, highlights different sensors that can be merged with other systems develop methods, such as optical, thermal infrared, multispectral, hyperspectral, light detection ranging radar. Second, using internet things reviewed. Third, shows platforms used a source technologies, ground-based (tractors robots), space-borne (satellites) aerial (unmanned vehicles) platforms. Finally, presents site-specific monitoring, nitrogen, chlorophyll, leaf area index, aboveground biomass, how improve these parameters. further reveals limitations previous provides recommendations their best available sensors. among airborne terrestrial LiDAR method crop, canopy, ground may considered futuristic easy-to-use low-cost solution enhance

Language: Английский

---

Enabling coastal blue carbon in Aotearoa New Zealand: opportunities and challenges

Frontiers in Marine Science, Journal Year: 2024, Volume and Issue: 11

Published: Feb. 7, 2024

Blue carbon is the sequestered by coastal and marine habitats such as mangroves, saltmarsh, seagrasses. The sequestration service provided these could help to mitigate climate change reducing greenhouse gas (GHG) emissions, well providing other important ecosystem services. Restoration of for purpose sequestering blue can generate credits, potentially offsetting costs restoration any lost revenue landowners. Coastal projects have been successfully implemented overseas, but a market has not yet established in Aotearoa New Zealand (ANZ). Here we identify key data gaps that will be necessary fill develop ANZ. Calculation abatement through development standardised method first step allow economic assessment potential sites. Economic determine if credits generated cover from restored lands. Once economically feasible sites identified, prioritisation determined value co-benefits produced (i.e., biodiversity). There are also legal uncertainties ANZ ownership foreshore contentious topic. Current legislation provides neither Crown nor person owns or own common area, although Māori may apply recognition customary rights, interests, title area. status property rights significant implications privately owned land, it unclear whether land considered when inundated future with sea level rise. Here, discuss further policy enablers including role government insurance industry encourage uptake private Filling assessments recognising Indigenous owners holders facilitate operationalising opportunities Zealand.

Language: Английский

---

Temporal Stability of Seagrass Extent, Leaf Area, and Carbon Storage in St. Joseph Bay, Florida: a Semi-automated Remote Sensing Analysis

Estuaries and Coasts, Journal Year: 2022, Volume and Issue: 45(7), P. 2082 - 2101

Published: March 15, 2022

Seagrasses are globally recognized for their contribution to blue carbon sequestration. However, accurate quantification of storage capacity remains uncertain due, in part, an incomplete inventory global seagrass extent and assessment its temporal variability. Furthermore, seagrasses undergoing significant decline globally, which highlights the urgent need develop change detection techniques applicable both scale loss spatial complexity coastal environments. This study applied a deep learning algorithmto 30-year time series Landsat 5 through 8 imagery quantify extent, leaf area index (LAI), belowground organic (BGC) St. Joseph Bay, Florida, between 1990 2020. Consistent with previous field-based observations regarding stability throughout there was no trend (23 ± 3 km2, τ = 0.09, p 0.59, n 31), LAI (1.6 0.2, -0.13, 0.42, or BGC (165 19 g C m-2, - 0.01, 0.1, 31) over period. There were, however, six brief declines years 2004 2019 following tropical cyclones, from recovered rapidly. Fine-scale interannual variability LAI, unrelated sea surface temperature climate associated El Niño-Southern Oscillation North Atlantic Oscillation. Although our showed that were stable Bay 2020, forecasts suggest environmental pressures ongoing, importance method presented here as valuable tool decadal-scale dynamics. Perhaps more importantly, results can serve baseline against we monitor future communities carbon.

Language: Английский

---

Mapping of Soil pH Based on SVM-RFE Feature Selection Algorithm

Agronomy, Journal Year: 2022, Volume and Issue: 12(11), P. 2742 - 2742

Published: Nov. 4, 2022

The explicit mapping of spatial soil pH is beneficial to evaluate the effects land-use changes in quality. Digital methods based on machine learning have been considered one effective way predict distribution parameters. However, selecting optimal environmental variables with an appropriate feature selection method key work digital mapping. In this study, we evaluated performance support vector recursive elimination (SVM-RFE) four common predicting and urban area Fuzhou, China. Thirty were collected from 134 samples that covered entire study for SVM-RFE selection. results identified five most critical value: mean annual temperature (MAT), slope, Topographic Wetness Index (TWI), modified soil-adjusted vegetation index (MSAVI), Band5. Further, algorithm could effectively improve model accuracy, extreme gradient boosting (XGBoost) after had best prediction (R2 = 0.68, MAE 0.16, RMSE 0.26). This paper combines RFE-SVM models enable fast inexpensive pH, providing new ideas at small medium scales, which will help conservation management region.

Language: Английский

---

Forest Aboveground Biomass Estimation in Küre Mountains National Park Using Multifrequency SAR and Multispectral Optical Data with Machine-Learning Regression Models

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(6), P. 1063 - 1063

Published: March 18, 2025

Aboveground biomass (AGB) is crucial in forest ecosystems and intricately linked to the carbon cycle global climate change dynamics. This study investigates efficacy of synthetic aperture radar (SAR) data from X, C, L bands, combined with Sentinel-2 optical imagery, vegetation indices, gray-level co-occurrence matrix (GLCM) texture metrics, topographical variables estimating AGB Küre Mountains National Park, Türkiye. Four machine-learning regression models were employed: partial least squares (PLS), absolute shrinkage selection operator (LASSO), multivariate linear, ridge regression. Among these, PLS (PLSR) model demonstrated highest accuracy estimation, achieving an R2 0.74, a mean error (MAE) 28.22 t/ha, root square (RMSE) 30.77 t/ha. An analysis across twelve revealed that integrating ALOS-2 PALSAR-2 SAOCOM L-band satellite data, particularly HV HH polarizations significantly enhances precision reliability estimations.

Language: Английский

---

Artificial Intelligence-Based color Reconstruction of Mogao Grottoes Murals Using Computer Vision Techniques

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(2)

Published: April 9, 2025

The Mogao Grottoes murals have deteriorated over centuries due to environmental exposure, pigment degradation, and natural ageing, making cultural heritage preservation difficult. AI computer vision can identify, classify, reconstruct faded pigments, revolutionizing color restoration. This reconstructs mural sections using deep learning, image processing, data implemented through TensorFlow, PyTorch OpenCV. study uses high-resolution Digital Dunhuang database images of 50 pigments categorized by color, stability, chemical composition. CNNs learning-based mapping algorithms detect fading suggest restorations pigments. reconstructions along with history accuracy expert evaluations records. Artificial intelligence-driven conservation detects precisely missing sections, matches restored colors historical authenticity, improving accuracy, efficiency, scalability. Scientifically, AI-based digital outperforms manual preserves faithfully sites artworks global learning-driven restoration models. first reproducible scientific model (CNN, GAN algorithms) analysis in was created.

Language: Английский

---