Hyperspectral data mining to identify relevant canopy spectral features for estimating durum wheat growth, nitrogen status, and grain yield

Thorp, Kelly R.; Wang, G.; Bronson, K. F.; Badaruddin, Mohammad; Mon, Jarai

doi:10.1016/j.compag.2017.02.024

Cited by 64 publications

(49 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several research studies based on spectral data are available, e.g., using data mining techniques with a genetic algorithm for nitrogen (N) status and grain yield estimation [10], or acquiring multispectral aerial images for the detection of wheat crop and weeds [11]. They are often based on measurements with one single sensor.…”

Section: Introductionmentioning

confidence: 99%

Utilisation of Ground and Airborne Optical Sensors for Nitrogen Level Identification and Yield Prediction in Wheat

et al. 2018

View full text Add to dashboard Cite

Abstract:A healthy crop growth ensures a good biomass development for optimal yield amounts and qualities. This can only be achieved with sufficient knowledge about field conditions. In this study we investigated the performance of optical sensors in large field trails, to predict yield and biomass characteristics. This publication investigated how information fusion can support farming decisions. We present the results of four site-year studies with one fluorescence sensor and two spectrometers mounted on a ground sensor platform, and one spectrometer built into a fixed-wing unmanned aerial vehicle (UAV). The measurements have been carried out in three winter wheat fields (Triticum aestivum L.) with different Nitrogen (N) levels. The sensor raw data have been processed and converted to features (indices and ratios) that correlate with field information and biological parameters. The aerial spectrometer indices showed correlations with the ground truth data only for site-year 2. FERARI (Fluorescence Excitation Ratio Anthocyanin Relative Index) and SFR (Simple Fluorescence Ratio) from the Multiplex ® Research fluorometer (MP) in 2012 showed significant correlations with yield (Adj. r 2 ≤ 0.63), and the NDVI (Normalised Difference Vegetation Index) and OSAVI (Optimized Soil-Adjusted Vegetation Index) of the FieldSpec HandHeld sensor (FS) even higher correlations with an Adj. r 2 ≤ 0.67. Concerning the available N (N avail ), the REIP (Red-Edge Inflection Point) and CropSpec indices from the FS sensor had a high correlation (Adj. r 2 ≤ 0.86), while the MP ratio SFR was slightly lower (Adj. r 2 ≤ 0.67). Concerning the biomass weight, the REIP and SAVI indices had an Adj. r 2 ≤ 0.78, and the FERARI and SFR ratios an Adj. r 2 ≤ 0.85. The indices of the HandySpec Field ® spectrometer gave a lower significance level than the FS sensor, and lower correlations (Adj. r 2 ≤ 0.64) over all field measurements. The features of MP and FS sensor have been used to create a feature fusion model. A developed linear model for site-year 4 has been used for evaluating the rest of the data sets. The used model did not correlate on a significant de novo level but by changing only one parameter, it resulted in a significant correlation. The data analysis reveals that by increasing mixed features from different sensors in a model, the higher and more robust the r 2 values became. New advanced algorithms, in combination with existent map overlay approaches, have the potential of complete and weighted decision fusion, to ensure the maximum yield for each specific field condition.

show abstract

Section: Introductionmentioning

confidence: 99%

Utilisation of Ground and Airborne Optical Sensors for Nitrogen Level Identification and Yield Prediction in Wheat

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The morpho-physiological traits of the crop, the weather variables, the knowledge of the farmer, the cultivation conditions, the use of sensors and spectroradiometric features of the culture, are inputs for predictive models (Lamba and Dhaka, 2014). Hyperspectral data from spectroradiometers have been applied to estimate wheat features such as nitrogen content, water content, and crop yield (Thorp et al, 2017) or yields maps from satellite data (Zheng et al, 2016) subjected to IF. Data extracted from a growth model and a radiative model have been coupled and fused by Zhang et al (2016), on the basis of vegetative indices and culture management parameters such as sowing date, sowing rate, and nitrogen rate.…”

Section: Precision Agriculturementioning

confidence: 99%

“…-The estimation of durum wheat growth, nitrogen status, and grain yield by hyperspectral data mining. The authors compared the spectral components to estimate the durum wheat traits, and developed a genetic algorithm to identify the most relevant spectral features; grain yield has been optimally estimated from canopy spectral measure mentsusing the genetic algorithm approach (Thorp et al, 2017).…”

Section: Data Science Applied To Durum Wheat Productionmentioning

confidence: 99%

Assessment of data fusion oriented on data mining approaches to enhance precision agriculture practices aimed at increase of Durum Wheat (Triticum turgidum L. var. durum) yield

D’Accolti¹,

Maggio²,

Massaro³

et al. 2018

J Food Nut Agri

View full text Add to dashboard Cite

In 2050, world population will reach a total of 9 billion inhabitants and their food demand have to be satisfied. Durum wheat (Triticum turgidum L. var. durum) is one of the most important food crop and its consumption is increasing worldwide. Productivity growth in agriculture and profitable returns are strongly influenced by investment in research and development, where Precision Agriculture (PA) represents an innovative way to manage farms by introducing the Information and Communication Technology (ICT) into the production process. It is known that farms activities produce large amounts of data. Today ICT allows, with electronic and software systems, to collect and transfer automatically these data, thus increasing yields and profits. In this direction significant data are processed from agricultural production, and retrieved to extract useful information important to increase the knowledge base. Data from multiple data sources can be processed by a Data Fusion (DF) approach able to combine multiple data sources into an unique database system. Raw data are transformed into useful information, thus DF improves pattern recognition, analysis of growth factors, and relationship between crops and environments. Data Fusion is synonym of Data Integration, Sensor Fusion, and Image Fusion. By means of Data Mining (DM) it is possible to extract useful information from data of the production processes thus providing new outputs concerning product quality and product “health status”. The following literature take into account the DF and DM techniques applied to Precision Agriculture (PA) and to cultivation inputs (water, nitrogen, etc.) management. We report also last advances of DF and DM in modern agriculture and in precision durum wheat production.

show abstract

“…Addressing the gaps in actual realized yield in the field requires much largerscale assessment of crop performance, in particular for oil palm, which is planted over several thousand hectares per estate and has a lifespan of over 20 years. Precision agriculture through hyperspectral imaging, satellite imaging, and detailed weather data recording allows crop fields to be assessed on a much larger scale [237][238][239][240]. Developments in this area will be essential in future to translate laboratoryscale experiments to commercial fields.…”

Section: Phenomics and Physiological Phenotypingmentioning

confidence: 99%

Review: Omics and Strategic Yield Improvement in Oil Crops

Teh

Neoh

Ithnin

et al. 2017

J Americ Oil Chem Soc

View full text Add to dashboard Cite

Crop yield improvement is essential for feeding the growing world population without concomitant increases in land allocated to agriculture. Oil crops are critical components of food supply as well as non-food applications. Oil palm is of particular value due to its significantly higher yield per unit area of land as compared to other oil crops. In the context of sustainable production of edible oils, this review will discuss the role of biochemical-omics techniques, including metabolomics, transcriptomics and proteomics research for yield improvement through plant breeding; in particular, the unique challenges of the mesocarp-oil bearing perennial crop, oil palm, are specifically discussed along with perspectives on what is needed for future crop improvement. Future oil crop improvement will need to go beyond classical trait selection, and omics research needs to go beyond looking at oil biosynthesis and fruit development. We need to explore carbon supply and flux, plant stress response, nutrient uptake and water use through a combination of genetics, biochemistry, epigenetics and gene interaction coupled to more detailed and continuous phenotypic data analysis.

show abstract

Hyperspectral data mining to identify relevant canopy spectral features for estimating durum wheat growth, nitrogen status, and grain yield

Cited by 64 publications

References 33 publications

Utilisation of Ground and Airborne Optical Sensors for Nitrogen Level Identification and Yield Prediction in Wheat

Utilisation of Ground and Airborne Optical Sensors for Nitrogen Level Identification and Yield Prediction in Wheat

Assessment of data fusion oriented on data mining approaches to enhance precision agriculture practices aimed at increase of Durum Wheat (Triticum turgidum L. var. durum) yield

Review: Omics and Strategic Yield Improvement in Oil Crops

Contact Info

Product

Resources

About