Abstract:ABSTRACT:Spectral yield models based on Vegetation Index (VI) and the mechanistic crop simulation models are being widely used for crop yield prediction. However, past experience has shown that the empirical nature of the VI based models and the intensive data requirement of the complex mechanistic models has limited their use for regional and spatial crop yield prediction especially for operational use. The present study was aimed at development of an intermediate method based on the use of remote sensing and… Show more
“…Tripathy et al (2014) also use a semi-empirical method, which incorporates physiological measures, spectral measures, and spatial features for estimating wheat yield [21]. The authors note that while spectral (empirical) and physics-based (mechanistic) models based on vegetation indices are widely used, they are respectively limited by being data-intensive and complex.…”
Interest in statistical analysis of remote sensing data to produce measurements of environment, agriculture, and sustainable development is established and continues to increase, and this is leading to a growing interaction between the earth science and statistical domains. With this in mind, we reviewed the literature on statistical machine learning methods commonly applied to remote sensing data. We focus particularly on applications related to the United Nations World Bank Sustainable Development Goals, including agriculture (food security), forests (life on land), and water (water quality). We provide a review of useful statistical machine learning methods, how they work in a remote sensing context, and examples of their application to these types of data in the literature. Rather than prescribing particular methods for specific applications, we provide guidance, examples, and case studies from the literature for the remote sensing practitioner and applied statistician. In the supplementary material, we also describe the necessary steps pre and post analysis for remote sensing data; the pre-processing and evaluation steps.
“…Tripathy et al (2014) also use a semi-empirical method, which incorporates physiological measures, spectral measures, and spatial features for estimating wheat yield [21]. The authors note that while spectral (empirical) and physics-based (mechanistic) models based on vegetation indices are widely used, they are respectively limited by being data-intensive and complex.…”
Interest in statistical analysis of remote sensing data to produce measurements of environment, agriculture, and sustainable development is established and continues to increase, and this is leading to a growing interaction between the earth science and statistical domains. With this in mind, we reviewed the literature on statistical machine learning methods commonly applied to remote sensing data. We focus particularly on applications related to the United Nations World Bank Sustainable Development Goals, including agriculture (food security), forests (life on land), and water (water quality). We provide a review of useful statistical machine learning methods, how they work in a remote sensing context, and examples of their application to these types of data in the literature. Rather than prescribing particular methods for specific applications, we provide guidance, examples, and case studies from the literature for the remote sensing practitioner and applied statistician. In the supplementary material, we also describe the necessary steps pre and post analysis for remote sensing data; the pre-processing and evaluation steps.
“…District level R&M crop yield was estimated using three different procedures: i) Agro-meteorological regression models (Singh et al, 2017), ii) Remote sensing index (VCI) based empirical models (Dubey et al, 2018) and iii) Semi physical Model (Tripathy et al, 2014;Chaurasiya et al, 2017). First approach was used by IMD (in collaboration with state agricultural universities), the second and third approaches were used by MNCFC.…”
<p><strong>Abstract.</strong> Rapeseed-mustard (<i>Brassica</i> spp.) is the major <i>rabi</i> oilseed crop of India. India is fourth largest contributor of oilseeds and Rapeseed-mustard contributing to around 11% of world’s total production and about 28.6% in total oilseeds production of the country. More than 85% Rapeseed-mustard production comes from 5 States viz. Rajasthan [48%], Haryana [12%], MP [10%], UP [9%] and West Bengal [7%]. In the previous few years, remote sensing technique has been progressively more considered for evolving as an alternative, standardized, possibly cheaper and faster technology for crop acreage estimation. Furthermore, satellite remote sensing data have strong advantages in comparison with other monitoring techniques because it provides timely, synoptic and latest information of crop at various stages over large scales. Therefore, under FASAL project, cloud free crop season’s images of different satellites (Sentinel-2, Resourcesat-2 and Landsat-8) were used and mustard crop was discriminated using Maximum Likelihood Classifier (MLC). Yield was estimated using different methods such as remote sensing derived NDVI, Agrometeorological yield model and Semi-Physical Model. The RMSE values for state level were found to be 4&ndash;17%, 8&ndash;19% and 13&ndash;23% for area, yield and production, respectively. The correlation coefficient (r) between DES and FASAL estimates were close to 0.9 in all the cases. The results of t-test at 5% level of significance inferred that FASAL and DES results were not significantly different. These results show that RS and weather-based techniques can be effectively used for pre-harvest acreage, yield and production estimation of mustard crop at district, state and national level.</p>
“…The model operates under the assumption of constant radiation conversion efficiency and harvest index, overlooking factors such as nitrogen deficiency influenced by water stress and temperature stress during reproductive and grain-filling stages. While nitrogen deficiency is addressed through fAPAR, the primary challenges affecting the accuracy of yield estimations are water and temperature stress [54].…”
This study underscores the critical importance of accurate crop yield information for national food security and export considerations, with a specific focus on wheat yield estimation at the Gram Panchayat (GP) level in Bareilly district, Uttar Pradesh, using technologies such as machine learning algorithms (ML), the Decision Support System for Agrotechnology Transfer (DSSAT) crop model and semi-physical models (SPMs). The research integrates Sentinel-2 time-series data and ground data to generate comprehensive crop type maps. These maps offer insights into spatial variations in crop extent, growth stages and the leaf area index (LAI), serving as essential components for precise yield assessment. The classification of crops employed spectral matching techniques (SMTs) on Sentinel-2 time-series data, complemented by field surveys and ground data on crop management. The strategic identification of crop-cutting experiment (CCE) locations, based on a combination of crop type maps, soil data and weather parameters, further enhanced the precision of the study. A systematic comparison of three major crop yield estimation models revealed distinctive gaps in each approach. Machine learning models exhibit effectiveness in homogenous areas with similar cultivars, while the accuracy of a semi-physical model depends upon the resolution of the utilized data. The DSSAT model is effective in predicting yields at specific locations but faces difficulties when trying to extend these predictions to cover a larger study area. This research provides valuable insights for policymakers by providing near-real-time, high-resolution crop yield estimates at the local level, facilitating informed decision making in attaining food security.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.