A Comparative Estimation of Maize Leaf Water Content Using Machine Learning Techniques and Unmanned Aerial Vehicle (UAV)-Based Proximal and Remotely Sensed Data

Determining maize water content variability is necessary for crop monitoring and in developing early warning systems to optimise agricultural production in smallholder farms. However, spatially explicit information on maize water content, particularly in Southern Africa, remains elementary due to the shortage of efficient and affordable primary sources of suitable spatial data at a local scale. Unmanned Aerial Vehicles (UAVs), equipped with light-weight multispectral sensors, provide spatially explicit, near-real-time information for determining the maize crop water status at farm scale. Therefore, this study evaluated the utility of UAV-derived multispectral imagery and machine learning techniques in estimating maize leaf water indicators: equivalent water thickness (EWT), fuel moisture content (FMC), and specific leaf area (SLA). The results illustrated that both NIR and red-edge derived spectral variables were critical in characterising the maize water indicators on smallholder farms. Furthermore, the best models for estimating EWT, FMC, and SLA were derived from the random forest regression (RFR) algorithm with an rRMSE of 3.13%, 1%, and 3.48%, respectively. Additionally, EWT and FMC yielded the highest predictive performance and were the most optimal indicators of maize leaf water content. The findings are critical towards developing a robust and spatially explicit monitoring framework of maize water status and serve as a proxy of crop health and the overall productivity of smallholder maize farms.

[1]  A. Skidmore,et al.  Retrieval of Specific Leaf Area From Landsat-8 Surface Reflectance Data Using Statistical and Physical Models , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[2]  Quan Wang,et al.  Retrieval of leaf fuel moisture contents from hyperspectral indices developed from dehydration experiments , 2017 .

[3]  K. Kawamura,et al.  Simple in‐field evaluation of moisture content in curing forage using normalized differece vegetation index (NDVI) , 2020 .

[4]  Anming Bao,et al.  Leaf and canopy water content estimation in cotton using hyperspectral indices and radiative transfer models , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[5]  Patrizia Busato,et al.  Machine Learning in Agriculture: A Review , 2018, Sensors.

[6]  H. Nieto,et al.  Crop water stress maps for an entire growing season from visible and thermal UAV imagery , 2016 .

[7]  Wei Gao,et al.  Physiological assessment of water deficit in soybean using midday leaf water potential and spectral features , 2019, Journal of Plant Interactions.

[8]  Mohammad Reza Mobasheri,et al.  Leaf Equivalent Water Thickness assessment using reflectance at optimum wavelengths , 2013 .

[9]  Amir Hossein Alavi,et al.  Machine learning in geosciences and remote sensing , 2016 .

[10]  E. Özelkan.  Water Body Detection Analysis Using NDWI Indices Derived from Landsat-8 OLI , 2020 .

[11]  Bing Lu,et al.  Evaluating Empirical Regression, Machine Learning, and Radiative Transfer Modelling for Estimating Vegetation Chlorophyll Content Using Bi-Seasonal Hyperspectral Images , 2019, Remote. Sens..

[12]  Guijun Yang,et al.  A Comparison of Regression Techniques for Estimation of Above-Ground Winter Wheat Biomass Using Near-Surface Spectroscopy , 2018, Remote. Sens..

[13]  Toshihiko Yamada,et al.  Determination of Leaf Water Content by Visible and Near-Infrared Spectrometry and Multivariate Calibration in Miscanthus , 2017, Front. Plant Sci..

[14]  S. Daryanto,et al.  Global Synthesis of Drought Effects on Maize and Wheat Production , 2016, PloS one.

[15]  Emilio Chuvieco,et al.  Combining AVHRR and meteorological data for estimating live fuel moisture content , 2008 .

[16]  José F. Moreno,et al.  Retrieval of canopy water content of different crop types with two new hyperspectral indices: Water Absorption Area Index and Depth Water Index , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[17]  Feng Zhang,et al.  Estimation of Canopy Water Content by Means of Hyperspectral Indices Based on Drought Stress Gradient Experiments of Maize in the North Plain China , 2015, Remote. Sens..

[18]  Onisimo Mutanga,et al.  UAV-based high-throughput phenotyping to increase prediction and selection accuracy in maize varieties under artificial MSV inoculation , 2021, Comput. Electron. Agric..

[19]  M. Cosh,et al.  Monitoring crop water content for corn and soybean fields through data fusion of MODIS and Landsat measurements in Iowa , 2020 .

[20]  Laura C. Bowling,et al.  Corn Response to Climate Stress Detected with Satellite-Based NDVI Time Series , 2016, Remote. Sens..

[21]  Danillo Roberto Pereira,et al.  A Machine Learning Approach for Mapping Forest Vegetation in Riparian Zones in an Atlantic Biome Environment Using Sentinel-2 Imagery , 2020, Remote. Sens..

[22]  O. Mutanga,et al.  The Utility of the Upcoming HyspIRI’s Simulated Spectral Settings in Detecting Maize Gray Leafy Spot in Relation to Sentinel-2 MSI, VENµS, and Landsat 8 OLI Sensors , 2019 .

[23]  F. Zhang,et al.  Estimation of vegetation water content using hyperspectral vegetation indices: a comparison of crop water indicators in response to water stress treatments for summer maize , 2019, BMC Ecology.

[24]  Jiali Shang,et al.  Retrieving Leaf and Canopy Water Content of Winter Wheat Using Vegetation Water Indices , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[25]  Ajay Sharda,et al.  Development and evaluation of thermal infrared imaging system for high spatial and temporal resolution crop water stress monitoring of corn within a greenhouse , 2016, Comput. Electron. Agric..

[26]  N. Al-Suhaibani,et al.  Potential of the existing and novel spectral reflectance indices for estimating the leaf water status and grain yield of spring wheat exposed to different irrigation rates , 2019, Agricultural Water Management.

[27]  Michael I. Miller,et al.  A comparison of random forest variable selection methods for classification prediction modeling , 2019, Expert Syst. Appl..

[28]  M. Moshelion,et al.  Measuring Arabidopsis, Tomato and Barley Leaf Relative Water Content (RWC) , 2015 .

[29]  Thomas Udelhoven,et al.  Challenges and Future Perspectives of Multi-/Hyperspectral Thermal Infrared Remote Sensing for Crop Water-Stress Detection: A Review , 2019, Remote. Sens..

[30]  Maggi Kelly,et al.  Remotely Sensed Water Limitation in Vegetation: Insights from an Experiment with Unmanned Aerial Vehicles (UAVs) , 2019, Remote. Sens..

[31]  A. Wahbi,et al.  In Situ Destructive Sampling , 2018 .

[32]  Huanhuan Yuan,et al.  A Comparison of Crop Parameters Estimation Using Images from UAV-Mounted Snapshot Hyperspectral Sensor and High-Definition Digital Camera , 2018, Remote. Sens..

[33]  Kathy Steppe,et al.  Can UAV-Based Infrared Thermography Be Used to Study Plant-Parasite Interactions between Mistletoe and Eucalypt Trees? , 2018, Remote. Sens..

[34]  Onisimo Mutanga,et al.  UAV-Based Multispectral Phenotyping for Disease Resistance to Accelerate Crop Improvement under Changing Climate Conditions , 2020, Remote. Sens..

[35]  Andrew K. Skidmore,et al.  Specific leaf area estimation from leaf and canopy reflectance through optimization and validation of vegetation indices , 2017 .

[36]  Xiangshan Zhou,et al.  Estimation of leaf water content from hyperspectral data of different plant species by using three new spectral absorption indices , 2021, PloS one.

[37]  Xiaodong Yang,et al.  Fuzzy Clustering of Maize Plant-Height Patterns Using Time Series of UAV Remote-Sensing Images and Variety Traits , 2019, Front. Plant Sci..

[38]  Emilio Chuvieco,et al.  Regional estimation of woodland moisture content by inverting Radiative Transfer Models , 2013 .

[39]  Guangsheng Zhou,et al.  Environmental explanation of maize specific leaf area under varying water stress regimes , 2020 .

[40]  Li Lin,et al.  Estimation of Leaf Nitrogen Content in Wheat Using New Hyperspectral Indices and a Random Forest Regression Algorithm , 2018, Remote. Sens..

[41]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[42]  Bruno Basso,et al.  Estimating plant distance in maize using Unmanned Aerial Vehicle (UAV) , 2018, PloS one.

[43]  A. Obi,et al.  Economic analysis of smallholder maize farmers: implications for public extension services in Eastern Cape , 2020 .

[44]  L. Riesgo,et al.  The Role of Smallholder Farms in Food and Nutrition Security , 2020 .

[45]  Hongxing Liu,et al.  Exploring the Potential of WorldView-2 Red-Edge Band-Based Vegetation Indices for Estimation of Mangrove Leaf Area Index with Machine Learning Algorithms , 2017, Remote. Sens..

[46]  Ola Hall,et al.  Remote Sensing of Yields: Application of UAV Imagery-Derived NDVI for Estimating Maize Vigor and Yields in Complex Farming Systems in Sub-Saharan Africa , 2018, Drones.

[47]  J. González,et al.  Physiological responses of quinoa (Chenopodium quinoa Willd.) to drought and waterlogging stresses: dry matter partitioning. , 2009 .

[48]  Wenting Han,et al.  Mapping Maize Water Stress Based on UAV Multispectral Remote Sensing , 2019, Remote. Sens..

[49]  Elfatih M. Abdel-Rahman,et al.  Random forest regression and spectral band selection for estimating sugarcane leaf nitrogen concentration using EO-1 Hyperion hyperspectral data , 2013 .

[50]  Reza Asadi,et al.  The use of support vector machine, neural network, and regression analysis to predict and optimize surface roughness and cutting forces in milling , 2019, The International Journal of Advanced Manufacturing Technology.

[51]  Rasmus Fensholt,et al.  Estimation of Herbaceous Fuel Moisture Content Using Vegetation Indices and Land Surface Temperature from MODIS Data , 2013, Remote. Sens..

[52]  Avi Bar-Massada,et al.  Utilizing Vegetation and Environmental New Micro Spacecraft (VENµS) Data to Estimate Live Fuel Moisture Content in Israel's Mediterranean Ecosystems , 2020, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[53]  D. Mulla.  Twenty five years of remote sensing in precision agriculture: Key advances and remaining knowledge gaps , 2013 .

[54]  Lu Li,et al.  Remote Estimation of Leaf and Canopy Water Content in Winter Wheat with Different Vertical Distribution of Water-Related Properties , 2015, Remote. Sens..

[55]  F. Castaldi,et al.  Assessing the potential of images from unmanned aerial vehicles (UAV) to support herbicide patch spraying in maize , 2017, Precision Agriculture.

[56]  S. Mousavi,et al.  Estimation of moisture in maize leaf by measuring leaf dielectric constant , 2008 .

[57]  T. Dube,et al.  Quantitative assessment of grassland foliar moisture parameters as an inference on rangeland condition in the mesic rangelands of southern Africa , 2021 .

[58]  Wang‐ting Yang,et al.  Differential responses of maize yield to drought at vegetative and reproductive stages , 2018, Plant, Soil and Environment.

[59]  Rabi N. Sahoo,et al.  Application of thermal imaging and hyperspectral remote sensing for crop water deficit stress monitoring , 2019, Geocarto International.

[60]  Liyuan Zhang,et al.  Maize Canopy Temperature Extracted From UAV Thermal and RGB Imagery and Its Application in Water Stress Monitoring , 2019, Front. Plant Sci..

[61]  C. Mutengwa,et al.  Estimation of Maize (Zea mays L.) Yield Per Harvest Area: Appropriate Methods , 2019, Agronomy.

[62]  Shusen Wang,et al.  Remote sensing of grassland–shrubland vegetation water content in the shortwave domain , 2006 .

[63]  Sadeed Hussain,et al.  Assessment of UAV-Onboard Multispectral Sensor for Non-Destructive Site-Specific Rapeseed Crop Phenotype Variable at Different Phenological Stages and Resolutions , 2020, Remote. Sens..

[64]  Pablo J. Zarco-Tejada,et al.  Estimation of fuel moisture content by inversion of radiative transfer models to simulate equivalent water thickness and dry matter content: analysis at leaf and canopy level , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[65]  O. Mutanga,et al.  Estimating soil organic carbon stocks under commercial forestry using topo-climate variables in KwaZulu-Natal, South Africa , 2020 .

[66]  Huanhuan Yuan,et al.  Retrieving Soybean Leaf Area Index from Unmanned Aerial Vehicle Hyperspectral Remote Sensing: Analysis of RF, ANN, and SVM Regression Models , 2017, Remote. Sens..

[67]  Peter Droogers,et al.  Effects of saline reclaimed waters and deficit irrigation on Citrus physiology assessed by UAV remote sensing , 2017 .

[68]  Ingunn Burud,et al.  Sequential forward selection and support vector regression in comparison to LASSO regression for spring wheat yield prediction based on UAV imagery , 2021, Comput. Electron. Agric..