Detection of the Optimal Temporal Windows for Mapping Paddy Rice Under a Double-Cropping System Using Sentinel-2 Imagery DOI Creative Commons
Li Sheng,

Y.F. Lv,

Zhouqiao Ren

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 17(1), P. 57 - 57

Published: Dec. 27, 2024

Accurately mapping paddy rice is crucial for food security, sustainable agricultural management and environmental protection. Recently, Sentinel-2 optical images with a spatial resolution of 10 m repeat cycle five days have demonstrated enormous potential fields. However, the influence temporal selection on still unclear. In this study, optimal windows were detected by considering all possible combinations during growing stages from constructed cloud-free 10-day time series assessing classification performances combination schemes F1_score. The results indicated that two or three phases necessary early-cropping (EP) late-cropping (LP), achieving F1_score aim 0.96. detection single-cropping (SP) requires to can obtain 0.94. Additionally, an automatic workflow has been developed, which does not require any cloud removal but provides complete coverage, suitable regions frequent rain clouds. Through verification in study area Yiwu, China, discrepancies between statistics within 5%, demonstrating rationality efficiency proposed framework.

Language: Английский

Integrating digital technologies in agriculture for climate change adaptation and mitigation: State of the art and future perspectives DOI
Carlos Parra-López, Saker Ben Abdallah, Guillermo Garcia‐Garcia

et al.

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 226, P. 109412 - 109412

Published: Sept. 7, 2024

Language: Английский

Citations

19
Wastewater treatment process enhancement based on multi-objective optimization and interpretable machine learning DOI
Tianxiang Liu, Heng Zhang,

Junhao Wu

et al.

Journal of Environmental Management, Journal Year: 2024, Volume and Issue: 364, P. 121430 - 121430

Published: June 13, 2024

Language: Английский

Citations

8
Remote sensing-based paddy yield estimation using physical and FCNN deep learning models in Gilan province, Iran DOI

Ehsan Asmar,

Mohammad H. Vahidnia, Mojtaba Rezaei

et al.

Remote Sensing Applications Society and Environment, Journal Year: 2024, Volume and Issue: 34, P. 101199 - 101199

Published: April 1, 2024

Language: Английский

Citations

2
Quantifying urban flood extent using satellite imagery and machine learning DOI
Rebecca Composto, Mirela G. Tulbure, Varun Tiwari

et al.

Natural Hazards, Journal Year: 2024, Volume and Issue: unknown

Published: July 27, 2024

Language: Английский

Citations

2
Hierarchical classification for improving parcel-scale crop mapping using time-series Sentinel-1 data DOI
Yanan Zhou,

Weiwei Zhu,

Li Feng

et al.

Journal of Environmental Management, Journal Year: 2024, Volume and Issue: 369, P. 122251 - 122251

Published: Aug. 29, 2024

Language: Английский

Citations

2
Digital mapping of dates of transplanting and accumulated thermal requirement of rice ( Oryza sativa L.) in the subtropics of North Eastern Hill Region, India DOI Creative Commons

Sushree Panda,

Vishram Ram,

Pradesh Jena

et al.

European Journal of Remote Sensing, Journal Year: 2024, Volume and Issue: 57(1)

Published: Sept. 30, 2024

Language: Английский

Citations

1
Automated rice mapping using multitemporal Sentinel-1 SAR imagery using dynamic threshold and slope-based index methods DOI
Aishwarya Hegde A.,

Pruthviraj Umesh,

Mohit P. Tahiliani

et al.

Remote Sensing Applications Society and Environment, Journal Year: 2024, Volume and Issue: unknown, P. 101410 - 101410

Published: Nov. 1, 2024

Language: Английский

Citations

1
Machine Learning-Based Summer Crops Mapping Using Sentinel-1 and Sentinel-2 Images DOI Creative Commons
Saeideh Maleki, Nicolas Baghdadi, Hassan Bazzi

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(23), P. 4548 - 4548

Published: Dec. 4, 2024

Accurate crop type mapping using satellite imagery is crucial for food security, yet accurately distinguishing between crops with similar spectral signatures challenging. This study assessed the performance of Sentinel-2 (S2) time series (spectral bands and vegetation indices), Sentinel-1 (S1) (backscattering coefficients polarimetric parameters), alongside phenological features derived from both S1 S2 (harmonic median features), classifying sunflower, soybean, maize. Random Forest (RF), Multi-Layer Perceptron (MLP), XGBoost classifiers were applied across various dataset configurations train-test splits over two sites years in France. Additionally, InceptionTime classifier, specifically designed data, was tested exclusively datasets to compare its against three general machine learning algorithms (RF, XGBoost, MLP). The results showed that outperformed RF MLP crops. optimal all combined backscattering indices, comparable data (mean F1 scores 89.9% 76.6% 91.1% maize). However, when individual sensors, while superior soybean Both produced close mean spatial, temporal, spatiotemporal transfer scenarios, though best choice transfer. Polarimetric did not yield effective results. classifier further improved classification accuracy crops, degree improvement varying by (the highest 90.6% 86.0% 93.5%

Language: Английский

Citations

1
Quantifying Urban Flood Extent Using Satellite Imagery and Random Forest: A Case Study in Southeastern Pennsylvania DOI Creative Commons
Rebecca Composto, Mirela G. Tulbure, Varun Tiwari

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: March 4, 2024

Abstract The risk of floods from tropical storms is increasing due to climate change and human development. Maps past flood extents can aid in planning mitigation efforts decrease risk. In 2021, Hurricane Ida slowed over the Mid-Atlantic Northeast United States released unprecedented rainfall. Satellite imagery Random Forest algorithm are a reliable combination map extents. However, this not usually applied urban areas. We used Sentinel-2 (10 m), along with derived indices, elevation, land cover data, as inputs model make new extent for southeastern Pennsylvania. was trained validated dataset created input PlanetScope (3 m) social media posts related event. overall accuracy 99%, class had user’s producer’s each 99%. then compared Federal Emergency Management Agency (FEMA) zones at county tract level found that more flooding occurred Minimal Hazard zone than 500-year zone. Our relies on publicly available data software efficiently accurately be deployed other Flood maps like one developed here help decision-makers focus recovery resilience.

Language: Английский

Citations

0
Advancing food security: Rice yield estimation framework using time-series satellite data & machine learning DOI Creative Commons
Varun Tiwari, Kelly R. Thorp, Mirela G. Tulbure

et al.

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(12), P. e0309982 - e0309982

Published: Dec. 12, 2024

Timely and accurately estimating rice yields is crucial for supporting food security management, agricultural policy development, climate change adaptation in rice-producing countries such as Bangladesh. To address this need, study introduced a workflow to enable timely precise yield estimation at sub-district scale (1,000-meter spatial resolution). However, significant gap exists the application of remote sensing methods government-reported management high resolution. Current are limited specific regions primarily used research, lacking integration into national reporting systems. Additionally, there no consistent yearly boro map scale, hindering localized decision-making. This leveraged MODIS annual district-level data train random forest model 1,000-meter resolution from 2002 2021. The results revealed mean percentage root square error (RMSE) 8.07% 12.96% when validation was conducted using reported district crop-cut data, respectively. estimated varies with an uncertainty range between 0.40 0.45 tons per hectare across Furthermore, trend analysis performed on 2021 modified Mann-Kendall test 95% confidence interval (p < 0.05). In Bangladesh, 23% area exhibits increasing yield, 0.11% shows decreasing trend, 76.51% demonstrates yield. Given that first attempt estimate over two decades mid-season estimates scalable space time, offering potential strengthening proposed can be easily applied other worldwide.

Language: Английский

Citations

0