Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline

Journals

Article Types

Countries / Regions

Search Results (2)

Search Parameters:
Keywords = remote sensing penology

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
28 pages, 8997 KiB  
Article
Deep Learning for Monitoring Agricultural Drought in South Asia Using Remote Sensing Data
by Foyez Ahmed Prodhan, Jiahua Zhang, Fengmei Yao, Lamei Shi, Til Prasad Pangali Sharma, Da Zhang, Dan Cao, Minxuan Zheng, Naveed Ahmed and Hasiba Pervin Mohana
Remote Sens. 2021, 13(9), 1715; https://doi.org/10.3390/rs13091715 - 28 Apr 2021
Cited by 70 | Viewed by 9045
Abstract
Drought, a climate-related disaster impacting a variety of sectors, poses challenges for millions of people in South Asia. Accurate and complete drought information with a proper monitoring system is very important in revealing the complex nature of drought and its associated factors. In [...] Read more.
Drought, a climate-related disaster impacting a variety of sectors, poses challenges for millions of people in South Asia. Accurate and complete drought information with a proper monitoring system is very important in revealing the complex nature of drought and its associated factors. In this regard, deep learning is a very promising approach for delineating the non-linear characteristics of drought factors. Therefore, this study aims to monitor drought by employing a deep learning approach with remote sensing data over South Asia from 2001–2016. We considered the precipitation, vegetation, and soil factors for the deep forwarded neural network (DFNN) as model input parameters. The study evaluated agricultural drought using the soil moisture deficit index (SMDI) as a response variable during three crop phenology stages. For a better comparison of deep learning model performance, we adopted two machine learning models, distributed random forest (DRF) and gradient boosting machine (GBM). Results show that the DFNN model outperformed the other two models for SMDI prediction. Furthermore, the results indicated that DFNN captured the drought pattern with high spatial variability across three penology stages. Additionally, the DFNN model showed good stability with its cross-validated data in the training phase, and the estimated SMDI had high correlation coefficient R2 ranges from 0.57~0.90, 0.52~0.94, and 0.49~0.82 during the start of the season (SOS), length of the season (LOS), and end of the season (EOS) respectively. The comparison between inter-annual variability of estimated SMDI and in-situ SPEI (standardized precipitation evapotranspiration index) showed that the estimated SMDI was almost similar to in-situ SPEI. The DFNN model provides comprehensive drought information by producing a consistent spatial distribution of SMDI which establishes the applicability of the DFNN model for drought monitoring. Full article
Show Figures

Graphical abstract

13 pages, 14199 KiB  
Article
Assimilating Remote Sensing Phenological Information into the WOFOST Model for Rice Growth Simulation
by Gaoxiang Zhou, Xiangnan Liu and Ming Liu
Remote Sens. 2019, 11(3), 268; https://doi.org/10.3390/rs11030268 - 30 Jan 2019
Cited by 40 | Viewed by 6194
Abstract
Precise simulation of crop growth is crucial to yield estimation, agricultural field management, and climate change. Although assimilation of crop model and remote sensing data has been applied in crop growth simulation, few studies have considered optimizing the crop model with respect to [...] Read more.
Precise simulation of crop growth is crucial to yield estimation, agricultural field management, and climate change. Although assimilation of crop model and remote sensing data has been applied in crop growth simulation, few studies have considered optimizing the crop model with respect to phenology. In this study, we assimilated phenological information obtained from Moderate Resolution Imaging Spectroradiometer (MODIS) time series data into the World Food Study (WOFOST) model to improve the accuracy of rice growth simulation at the regional scale. The particle swarm optimization (PSO) algorithm was implemented to optimize the initial phenology development stage (IDVS) and transplanting date (TD) in the WOFOST model by minimizing the difference between simulated and observed phenology, including heading and maturity date. Assimilating phenology improved the accuracy of the rice growth simulation, with correlation coefficients (R) equal to 0.793, 0822, and 0.813 at three fieldwork dates. The performance of the proposed strategy is comparable with that of the enhanced vegetation index (EVI) time series assimilation strategy, with less computation time. Additionally, the result confirms that the proposed strategy could be applied with different spatial resolution images and the difference of simulated LAImean is less than 0.35 in three experimental areas. This study offers a novel assimilation strategy with regard to the phenology development process, which is efficient and scalable for crop growth simulation. Full article
Show Figures

Graphical abstract

Back to TopTop