Limitations of cloud cover for optical remote sensing of agricultural areas across South America

Prudente, Victor Hugo Rohden; Martins, Vitor Souza; Vieira, D. C.; Silva, Nildson Rodrigues de França e; Adami, Marcos; Sanches, I. D.

doi:10.1016/j.rsase.2020.100414

Cited by 31 publications

(36 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Proximal (or terrestrial) sensors suffering less atmospheric interference than aerial and orbital sensors (Eberhardt et al, 2016;Prudente et al, 2020;Whitcraft, Vermote, Becker-Reshef, & Justice, 2015) and have temporal resolution flexibility (Mulla, 2013). Some studies characterized biophysical crop proprieties using proximal VI from active and passive sensors (Anderson et al, 2016;Cattani et al, 2017;Congalton, Gu, Yadav, Thenkabail, & Ozdogan, 2014;Prudente et al, 2019;Viana et al, 2018;Viana, Mercante, Felipetto, Kusminski, & Bleil Jr, 2017;Yao et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

Comparison Between Vegetation Index Obtained by Active and Passive Proximal Sensors

Prudente¹,

Mercante²,

Johann³

et al. 2022

JAS

Self Cite

View full text Add to dashboard Cite

Proximal sensors have been used to characterize the crop biophysical properties by reflectance values and/or using Vegetation Indices (IV). Our goal with this work is to compare NDVI (Normalized Difference Vegetation Index) spectra-temporal profiles obtained by active (GreenSeeker 505 Handheld) and passive (FieldSpec4 model Standard-Res) proximal sensors to monitor soybeans and beans. It was monitored agricultural fields with soybeans Nidera 5909RG variety and beans Imperador variety, located in the municipality of Cascavel, Parana state, Brazil. The proximal sensors were used to monitor the crop's conditions on different Days After Sowing (DAS). NDVI from FieldSpec4 (NDVI FS) showed a higher correlation with GreenSeeker NDVI (NDVI GS) in the wavelengths of 649 nm and 771 nm for soybeans (rs = 0.9105) and 646 nm and 792 nm for beans (rs = 0.9382). The inter-calibration of NDVI GS values in function of NDVI FS, considering the entire phenological cycle, resulted in RMSE = 0.0520 and dr = 0.8630 for soybeans and RMSE = 0.0636 and dr = 0.8890 for beans. NDVI values showed saturation during the major vegetative development of the crops, interfering in the inter-calibration process. In general, the NDVI GS and NDVI FS were similar in terms of their spectral-temporal pattern. According to our results, the active sensor could be used to crop monitoring, resulting in a lower cost and less climatic interference.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparison Between Vegetation Index Obtained by Active and Passive Proximal Sensors

Prudente¹,

Mercante²,

Johann³

et al. 2022

JAS

Self Cite

View full text Add to dashboard Cite

show abstract

“…To perform the semantic segmentation in the loss function, the authors used a Multi-Layer Perceptron (MLP) network. The objective function of the proposed method is presented in Equation (9):…”

Section: Proposed Methodsmentioning

confidence: 99%

“…On average, about 55% of the Earth's land surface is covered by clouds [8]. In South America, cropland areas can have up to 80% cloud cover frequency during the rainy season from December to February, making agricultural monitoring through optical satellite images challenging in this region [9]. Therefore, to deliver high-quality agricultural statistics using multi-temporal optical satellite images, it is essential to develop methods for cloud removal in satellite images [10].…”

Section: Introductionmentioning

confidence: 99%

Pix2pix Conditional Generative Adversarial Network with MLP Loss Function for Cloud Removal in a Cropland Time Series

et al. 2021

View full text Add to dashboard Cite

Clouds are one of the major limitations to crop monitoring using optical satellite images. Despite all efforts to provide decision-makers with high-quality agricultural statistics, there is still a lack of techniques to optimally process satellite image time series in the presence of clouds. In this regard, in this article it was proposed to add a Multi-Layer Perceptron loss function to the pix2pix conditional Generative Adversarial Network (cGAN) objective function. The aim was to enforce the generative model to learn how to deliver synthetic pixels whose values were proxies for the spectral response improving further crop type mapping. Furthermore, it was evaluated the generalization capacity of the generative models in producing pixels with plausible values for images not used in the training. To assess the performance of the proposed approach it was compared real images with synthetic images generated with the proposed approach as well as with the original pix2pix cGAN. The comparative analysis was performed through visual analysis, pixel values analysis, semantic segmentation and similarity metrics. In general, the proposed approach provided slightly better synthetic pixels than the original pix2pix cGAN, removing more noise than the original pix2pix algorithm as well as providing better crop type semantic segmentation; the semantic segmentation of the synthetic image generated with the proposed approach achieved an F1-score of 44.2%, while the real image achieved 44.7%. Regarding the generalization, the models trained utilizing different regions of the same image provided better pixels than models trained using other images in the time series. Besides this, the experiments also showed that the models trained using a pair of images selected every three months along the time series also provided acceptable results on images that do not have cloud-free areas.

show abstract

“…Despite the resolution-related advances described previously, most notably in the tropics, the following factors hinder practical applications of RS-based IS in crops: the high-resolution RS datasets required to schedule irrigation at a plot scale (Calera et al, 2017) do not have a high-frequent revisiting time needed to daily track the soil water depletion (Li and Roy, 2017); the high-cloud coverage in the tropical hillslope areas evidenced for most of the year (Prudente et al, 2020), does not provide cloud-free time series pixels to compute the irrigation parameters; although most studies in table 3 did not include precipitation in water balance, it has a critical influence on the soil water balance (SWB) throughout the year (Richter, 2016); and some RS models required to compute ET such as METRIC (Olmedo and de la Fuente-Saiz, 2018), must be calibrated with hourly climate data corresponding to the area of interest.…”

Section: Rs Applications In Agriculture: Irrigation Traitsmentioning

confidence: 99%

“…Moreover, the soil moisture can be retrieved through optical and radar satellite images (Calera et al, 2017). As the optical images acquisition process is hampered by the high cloud coverage in the tropics (Prudente et al, 2020) and highly conditioned by target-surface-reflectance properties (Dorigo et al, 2015), radar sensors can work 24 h a day while not being affected by the atmospheric scattering and while controlling the energy emitted to the target surface (Tempfli et al, 2009).…”

Section: Soil Moisture Retrieval From Sar Imagesmentioning

confidence: 99%

Advances in Hass avocado irrigation scheduling under digital agriculture approach

Erazo-Mesa

Echeverri-Sánchez

Ramírez‐Gil

2022

Rev. Colomb. Cienc. Hortic.

View full text Add to dashboard Cite

Under tropical conditions, Hass avocado irrigation is a controversial issue due to insufficient scientific evidence. The rapid progression of technological advances and its incorporation in agriculture have expanded options to improve the irrigation scheduling (IS) of Hass avocado. The concept featuring those technological advances in agriculture is digital agriculture (DA). Here, we present a mixture of well-known studies in the Hass avocado irrigation focused on proximal sensing (PS) technologies and recent studies emphasizing the potential of remote sensing (RS), and application technologies to schedule the irrigation. PS takes advantage of the soil or trees' proximity to output reliable measurements with a high temporal resolution, while RS provides a broad set of spectral data in continuous and large areas that can be transformed into crop-related biophysical variables. Applications – a term grouping mobile (smartphone) apps, desktop programs, and web-based platforms – offers portability, high precision, and graphic visualization of variables obtained or estimated by sensors. Integrating RS and PS technologies through user-friendly applications can represent a suitable option to improve Hass avocado irrigation in developing countries. Our review is presented in the following sections: general introduction, DA approach definition, use of proximal sensing, use of remote sensing, and scheduling irrigation applications.

show abstract

Limitations of cloud cover for optical remote sensing of agricultural areas across South America

Cited by 31 publications

References 41 publications

Comparison Between Vegetation Index Obtained by Active and Passive Proximal Sensors

Comparison Between Vegetation Index Obtained by Active and Passive Proximal Sensors

Pix2pix Conditional Generative Adversarial Network with MLP Loss Function for Cloud Removal in a Cropland Time Series

Advances in Hass avocado irrigation scheduling under digital agriculture approach

Contact Info

Product

Resources

About