The Application of an Unmanned Aerial System and Machine Learning Techniques for Red Clover-Grass Mixture Yield Estimation under Variety Performance Trials

A significant trend has developed with the recent growing interest in the estimation of aboveground biomass of vegetation in legume-supported systems in perennial or semi-natural grasslands to meet the demands of sustainable and precise agriculture. Unmanned aerial systems (UAS) are a powerful tool when it comes to supporting farm-scale phenotyping trials. In this study, we explored the variation of the red clover-grass mixture dry matter (DM) yields between temporal periods (one- and two-year cultivated), farming operations [soil tillage methods (STM), cultivation methods (CM), manure application (MA)] using three machine learning (ML) techniques [random forest regression (RFR), support vector regression (SVR), and artificial neural network (ANN)] and six multispectral vegetation indices (VIs) to predict DM yields. The ML evaluation results showed the best performance for ANN in the 11-day before harvest category (R2 = 0.90, NRMSE = 0.12), followed by RFR (R2 = 0.90 NRMSE = 0.15), and SVR (R2 = 0.86, NRMSE = 0.16), which was furthermore supported by the leave-one-out cross-validation pre-analysis. In terms of VI performance, green normalized difference vegetation index (GNDVI), green difference vegetation index (GDVI), as well as modified simple ratio (MSR) performed better as predictors in ANN and RFR. However, the prediction ability of models was being influenced by farming operations. The stratified sampling, based on STM, had a better model performance than CM and MA. It is proposed that drone data collection was suggested to be optimum in this study, closer to the harvest date, but not later than the ageing stage.

[1]  Ming-Der Yang,et al.  Spatial and Spectral Hybrid Image Classification for Rice Lodging Assessment through UAV Imagery , 2017, Remote. Sens..

[2]  Roberto Fanigliulo,et al.  Light Drone-Based Application to Assess Soil Tillage Quality Parameters , 2020, Sensors.

[3]  M. Wachendorf,et al.  Remote sensing as a tool to assess botanical composition, structure, quantity and quality of temperate grasslands , 2018 .

[4]  Bruno Basso,et al.  Estimation of spatial and temporal variability of pasture growth and digestibility in grazing rotations coupling unmanned aerial vehicle (UAV) with crop simulation models , 2019, PloS one.

[5]  Daniele Pochi,et al.  Effects of six primary tillage implements on energy inputs and residue cover in Central Italy , 2016 .

[6]  R. Rees,et al.  Potential of legume-based grassland–livestock systems in Europe: a review , 2013, Grass and forage science : the journal of the British Grassland Society.

[7]  Jonathan Li,et al.  Predicting Canopy Nitrogen Content in Citrus-Trees Using Random Forest Algorithm Associated to Spectral Vegetation Indices from UAV-Imagery , 2019, Remote. Sens..

[8]  E. Honkavaara,et al.  Machine learning estimators for the quantity and quality of grass swards used for silage production using drone-based imaging spectrometry and photogrammetry , 2020 .

[9]  I. Roldán‐Ruiz,et al.  Factors Underlying Seed Yield in Red Clover: Review of Current Knowledge and Perspectives , 2019, Agronomy.

[10]  M. Raizada,et al.  Belowground nitrogen transfer from legumes to non-legumes under managed herbaceous cropping systems. A review , 2016, Agronomy for Sustainable Development.

[11]  M. Kearns,et al.  Algorithmic stability and sanity-check bounds for leave-one-out cross-validation , 1999 .

[12]  T. Astor,et al.  The potential of UAV-borne spectral and textural information for predicting aboveground biomass and N fixation in legume-grass mixtures , 2020, PloS one.

[13]  Li Zhang,et al.  Above-ground biomass estimation and yield prediction in potato by using UAV-based RGB and hyperspectral imaging , 2020 .

[14]  J. Wolf,et al.  Yield gap analysis with local to global relevance—A review , 2013 .

[15]  J. Hampton,et al.  Legume Seed Production Meeting Market Requirements and Economic Impacts , 2015 .

[16]  J. Peñuelas,et al.  Remote sensing of biomass and yield of winter wheat under different nitrogen supplies , 2000 .

[17]  Yanjie Wang,et al.  Estimation of Winter Wheat Above-Ground Biomass Using Unmanned Aerial Vehicle-Based Snapshot Hyperspectral Sensor and Crop Height Improved Models , 2017, Remote. Sens..

[18]  Yiping Ren,et al.  The predictive performances of random forest models with limited sample size and different species traits , 2020 .

[19]  Timothy Smith,et al.  Climate Benefits of Increasing Plant Diversity in Perennial Bioenergy Crops , 2019 .

[20]  E. Brummer,et al.  Achievements and Challenges in Improving Temperate Perennial Forage Legumes , 2015 .

[21]  C. Jordan.  Derivation of leaf-area index from quality of light on the forest floor , 1969 .

[22]  C. Drury,et al.  Legume Cover Crops Provide Nitrogen to Corn During a Three‐Year Transition to Organic Cropping , 2019, Agronomy Journal.

[23]  Chunhua Zhang,et al.  The application of small unmanned aerial systems for precision agriculture: a review , 2012, Precision Agriculture.

[24]  Junho Yeom,et al.  A novel framework to detect conventional tillage and no-tillage cropping system effect on cotton growth and development using multi-temporal UAS data , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[25]  F. Loreto,et al.  Opportunities and Limitations of Crop Phenotyping in Southern European Countries , 2019, Front. Plant Sci..

[26]  Eija Honkavaara,et al.  A Novel Machine Learning Method for Estimating Biomass of Grass Swards Using a Photogrammetric Canopy Height Model, Images and Vegetation Indices Captured by a Drone , 2018 .

[27]  M. Balzarini,et al.  Red clover (Trifolium pratense L.) seedling density in mixed pastures as predictor of annual yield , 2020 .

[28]  Junho Yeom,et al.  Comparison of Vegetation Indices Derived from UAV Data for Differentiation of Tillage Effects in Agriculture , 2019, Remote. Sens..

[29]  Weixing Cao,et al.  Predicting grain yield in rice using multi-temporal vegetation indices from UAV-based multispectral and digital imagery , 2017 .

[30]  H. Piepho,et al.  Genetic and non-genetic long-term trends of 12 different crops in German official variety performance trials and on-farm yield trends , 2014, Theoretical and Applied Genetics.

[31]  G. Mozgeris,et al.  Imaging from manned ultra-light and unmanned aerial vehicles for estimating properties of spring wheat , 2018, Precision Agriculture.

[32]  K. Steenwerth,et al.  Nitrous Oxide Production From Soils in the Future: Processes, Controls, and Responses to Climate Change , 2018 .

[33]  Christian Brodbeck,et al.  Multispectral UAS Data Accuracy for Different Radiometric Calibration Methods , 2019, Remote. Sens..

[34]  J. G. White,et al.  Aerial Color Infrared Photography for Determining Early In‐Season Nitrogen Requirements in Corn , 2005 .

[35]  Lei Zhang,et al.  A comparison of two models with Landsat data for estimating above ground grassland biomass in Inner Mongolia, China , 2009 .

[36]  Michael Wachendorf,et al.  Prediction of yield and the contribution of legumes in legume-grass mixtures using field spectrometry , 2009, Precision Agriculture.

[37]  Guijun Yang,et al.  A rapid monitoring of NDVI across the wheat growth cycle for grain yield prediction using a multi-spectral UAV platform. , 2019, Plant science : an international journal of experimental plant biology.

[38]  A. Skidmore,et al.  Integrating imaging spectroscopy and neural networks to map grass quality in the Kruger National Park, South Africa , 2004 .

[39]  L. Roth,et al.  Predicting cover crop biomass by lightweight UAS-based RGB and NIR photography: an applied photogrammetric approach , 2018, Precision Agriculture.

[40]  O. E. Ansín,et al.  Combining Ability in Mixtures of Prairie Grass and Clovers , 2012 .

[41]  Kaihui Song,et al.  Estimation methods developing with remote sensing information for energy crop biomass: A comparative review , 2019, Biomass and Bioenergy.

[42]  Tao Liu,et al.  Comparing fully convolutional networks, random forest, support vector machine, and patch-based deep convolutional neural networks for object-based wetland mapping using images from small unmanned aircraft system , 2018 .

[43]  Helge Bonesmo *,et al.  Evaluating an image analysis system for mapping white clover pastures , 2004 .

[44]  Gregory J. McDermid,et al.  A Systematic Review of the Factors Influencing the Estimation of Vegetation Aboveground Biomass Using Unmanned Aerial Systems , 2020, Remote. Sens..

[45]  G. Sassenrath,et al.  Soft winter wheat outyields hard winter wheat in a subhumid environment: Weather drivers, yield plasticity, and rates of yield gain , 2020 .

[46]  H. Jin Kim,et al.  Model predictive flight control using adaptive support vector regression , 2010, Neurocomputing.

[47]  Claudia Notarnicola,et al.  Review of Machine Learning Approaches for Biomass and Soil Moisture Retrievals from Remote Sensing Data , 2015, Remote. Sens..

[48]  José M. Bengochea-Guevara,et al.  Comparing UAV-Based Technologies and RGB-D Reconstruction Methods for Plant Height and Biomass Monitoring on Grass Ley , 2019, Sensors.

[49]  A. Tsunekawa,et al.  Quantifying Grazing Intensity Using Remote Sensing in Alpine Meadows on Qinghai-Tibetan Plateau , 2019, Sustainability.

[50]  Ming-Der Yang,et al.  Semantic Segmentation Using Deep Learning with Vegetation Indices for Rice Lodging Identification in Multi-date UAV Visible Images , 2020, Remote. Sens..

[51]  Baofeng Su,et al.  Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications , 2017, J. Sensors.

[52]  Zhou Zhang,et al.  Prediction of sorghum biomass based on image based features derived from time series of UAV images , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[53]  Peter Surový,et al.  UAV RTK/PPK Method - An Optimal Solution for Mapping Inaccessible Forested Areas? , 2019, Remote. Sens..

[54]  Hengbiao Zheng,et al.  Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery , 2018, Precision Agriculture.

[55]  Muhammad Hamid Chaudhry,et al.  A comparative study of modern UAV platform for topographic mapping , 2020, IOP Conference Series: Earth and Environmental Science.

[56]  David B. Roy,et al.  Declines in forage availability for bumblebees at a national scale , 2006 .

[57]  Peijun Du,et al.  A review of supervised object-based land-cover image classification , 2017 .

[58]  L. Kumar,et al.  Estimating and mapping grass phosphorus concentration in an African savanna using hyperspectral image data , 2007 .

[59]  Kevin F. Smith,et al.  Using Sensors and Unmanned Aircraft Systems for High-Throughput Phenotyping of Biomass in Perennial Ryegrass Breeding Trials , 2019, Front. Plant Sci..

[60]  Hemerson Pistori,et al.  A random forest ranking approach to predict yield in maize with uav-based vegetation spectral indices , 2020, Comput. Electron. Agric..

[61]  Adrien Michez,et al.  How Far Can Consumer-Grade UAV RGB Imagery Describe Crop Production? A 3D and Multitemporal Modeling Approach Applied to Zea mays , 2018, Remote. Sens..

[62]  Hao Yang,et al.  Unmanned Aerial Vehicle Remote Sensing for Field-Based Crop Phenotyping: Current Status and Perspectives , 2017, Front. Plant Sci..

[63]  U. Schurr,et al.  Plant Phenotyping: Past, Present, and Future , 2019, Plant phenomics.

[64]  S. Shafian,et al.  Assessment of UAV Based Vegetation Indices for Nitrogen Concentration Estimation in Spring Wheat , 2018 .

[65]  J. Deckers,et al.  World Reference Base for Soil Resources , 1998 .

[66]  K. Sepp,et al.  Fine scale plant community assessment in coastal meadows using UAV based multispectral data , 2020, Ecological Indicators.

[67]  S. Robinson,et al.  Food Security: The Challenge of Feeding 9 Billion People , 2010, Science.

[68]  J. Théau,et al.  Estimation of forage biomass and vegetation cover in grasslands using UAV imagery , 2021, PloS one.

[69]  R. Ellis,et al.  Progress and Challenges in Ex Situ Conservation of Forage Germplasm: Grasses, Herbaceous Legumes and Fodder Trees , 2020, Plants.

[70]  Karin Kollo,et al.  Modernization of the Estonian National GNSS Reference Station Network , 2018 .

[71]  J. Chen.  Evaluation of Vegetation Indices and a Modified Simple Ratio for Boreal Applications , 1996 .

[72]  J. Araus,et al.  Field high-throughput phenotyping: the new crop breeding frontier. , 2014, Trends in plant science.

[73]  M. V. D. van der Heijden,et al.  Cover crops as a tool to reduce reliance on intensive tillage and nitrogen fertilization in conventional arable cropping systems , 2020, Field Crops Research.

[74]  Michael Wachendorf,et al.  Biomass Prediction of Heterogeneous Temperate Grasslands Using an SfM Approach Based on UAV Imaging , 2019, Agronomy.