Geospatial Approach to Assess the Impact of Nutrients on Rice Equivalent Yield Using MODIS Sensors’-Based MOD13Q1-NDVI Data

Pandey, Prem C.; Mandal, Vinay Prasad; Katiyar, Swati; Kumar, Pavan; Tomar, Vandana; Patairiya, Shashikanta; Ravisankar, N.; Gangwar, B.

doi:10.1109/jsen.2015.2451113

Cited by 23 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Waring et al (2006) determined that MODIS enhanced vegetation index (EVI) values at a spatial resolution of 1-km provide similar information to values derived from localized field sampling, i.e., areal averages of in-situ data were comparable with the 1-km MODIS resolution as measured by correlations between MODIS EVI and field survey data of tree richness in eco-regions across the contiguous U.S.A. In other examples, Tomar et al (2014) and Pandey et al (2015) employed MODIS NDVI products in the study of rice equivalent yield, while Zhang et al (2003) utilized them to monitor vegetation phenology on an area located in New England, USA, and concluded that the results obtained from their investigation were both geographically and ecologically consistent with the pattern of vegetation transition behaviour in the region determined by previous field-based studies. These studies demonstrate that the MODIS sensors are able to provide an adequate and meaningful measure of vegetation across a large surface area.…”

Section: Introductionmentioning

confidence: 74%

Impacts of extreme climate on Australia's green cover (2003–2018): A MODIS and mascon probe

Saleem

Awange

Kühn

et al. 2021

Science of The Total Environment

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 74%

Impacts of extreme climate on Australia's green cover (2003–2018): A MODIS and mascon probe

Saleem

Awange

Kühn

et al. 2021

Science of The Total Environment

View full text Add to dashboard Cite

“…NDVI and soil N concentrations have a positive correlation, i.e., a higher NDVI value is associated with a larger amount of N in the soil. In addition, NDVI values are also sensitive to the efficiency of N use by vegetation [38][39]. Similarly, NDVI and soil P concentrations also have a positive correlation, whereby higher NDVI values suggest higher soil P concentrations [40][41][42].…”

Section: Creation Of Ndvi(n) and Ndvi(p)mentioning

confidence: 99%

Relations between Microtopography and Soil N and P Observed by an Unmanned Aerial Vehicle and Satellite Remote Sensing (GF-2)

Lou

Ren

Yang

et al. 2020

Pol. J. Environ. Stud.

View full text Add to dashboard Cite

Topography, which reflects the variation in elevation of the earth's surface, has many influences on the allocation of energy and materials [1]. Microtopography which describes the topography on the fine scale also has direct impacts on vegetation and soil [2-3]. For example, microtopography can affect the diversity of vegetation, plant biomass, and chemical elements [4]. The concentration of soil nutrients such as N and P changes with variation of soil moisture, solar energy,

show abstract

“…They generate computational models that attempt to approximate the behavior of the field based on the observed relationships between multi-source covariate factors and crop yield. Some approaches use remotely sensed data as covariate factors, such as satellite imagery captured by the Moderate Resolution Imaging Spectroradiometer (MODIS) and Sentinel missions [ 15 , 16 , 17 ]. Other approaches incorporate on-ground data; that is, data acquired directly from the field, such as soil electroconductivity or nitrogen rate [ 18 , 19 ].…”

Section: Introductionmentioning

confidence: 99%

Improved Yield Prediction of Winter Wheat Using a Novel Two-Dimensional Deep Regression Neural Network Trained via Remote Sensing

Morales

Sheppard

Hegedus

et al. 2023

Sensors

View full text Add to dashboard Cite

In recent years, the use of remotely sensed and on-ground observations of crop fields, in conjunction with machine learning techniques, has led to highly accurate crop yield estimations. In this work, we propose to further improve the yield prediction task by using Convolutional Neural Networks (CNNs) given their unique ability to exploit the spatial information of small regions of the field. We present a novel CNN architecture called Hyper3DNetReg that takes in a multi-channel input raster and, unlike previous approaches, outputs a two-dimensional raster, where each output pixel represents the predicted yield value of the corresponding input pixel. Our proposed method then generates a yield prediction map by aggregating the overlapping yield prediction patches obtained throughout the field. Our data consist of a set of eight rasterized remotely-sensed features: nitrogen rate applied, precipitation, slope, elevation, topographic position index (TPI), aspect, and two radar backscatter coefficients acquired from the Sentinel-1 satellites. We use data collected during the early stage of the winter wheat growing season (March) to predict yield values during the harvest season (August). We present leave-one-out cross-validation experiments for rain-fed winter wheat over four fields and show that our proposed methodology produces better predictions than five compared methods, including Bayesian multiple linear regression, standard multiple linear regression, random forest, an ensemble of feedforward networks using AdaBoost, a stacked autoencoder, and two other CNN architectures.

show abstract

Geospatial Approach to Assess the Impact of Nutrients on Rice Equivalent Yield Using MODIS Sensors’-Based MOD13Q1-NDVI Data

Cited by 23 publications

References 16 publications

Impacts of extreme climate on Australia's green cover (2003–2018): A MODIS and mascon probe

Impacts of extreme climate on Australia's green cover (2003–2018): A MODIS and mascon probe

Relations between Microtopography and Soil N and P Observed by an Unmanned Aerial Vehicle and Satellite Remote Sensing (GF-2)

Improved Yield Prediction of Winter Wheat Using a Novel Two-Dimensional Deep Regression Neural Network Trained via Remote Sensing

Contact Info

Product

Resources

About