Comparison of Machine-Learning and CASA Models for Predicting Apple Fruit Yields from Time-Series Planet Imageries

Apple (Malus domestica Borkh. cv. “Fuji”), an important cash crop, is widely consumed around the world. Accurately predicting preharvest apple fruit yields is critical for planting policy making and agricultural management. This study attempted to explore an effective approach for predicting apple fruit yields based on time-series remote sensing data. In this study, time-series vegetation indices (VIs) were derived from Planet images and analyzed to further construct an accumulated VI (∑VIs)-based random forest (RF∑VI) model and a Carnegie–Ames–Stanford approach (CASA) model for predicting apple fruit yields. The results showed that (1) ∑NDVI was the optimal predictor to construct an RF model for apple fruit yield, and the R2, RMSE, and RPD values of the RF∑NDVI model reached 0.71, 16.40 kg/tree, and 1.83, respectively. (2) The maximum light use efficiency was determined to be 0.499 g C/MJ, and the CASASR model (R2 = 0.57, RMSE = 19.61 kg/tree, and RPD = 1.53) performed better than the CASANDVI model and the CASAAverage model (R2, RMSE, and RPD = 0.56, 24.47 kg/tree, 1.22 and 0.57, 20.82 kg/tree, 1.44, respectively). (3) This study compared the yield prediction accuracies obtained by the models using the same dataset, and the RF∑NDVI model (RPD = 1.83) showed a better performance in predicting apple fruit yields than the CASASR model (RPD = 1.53). The results obtained from this study indicated the potential of the RF∑NDVI model based on time-series Planet images to accurately predict apple fruit yields. The models could provide spatial and quantitative information of apple fruit yield, which would be valuable for agronomists to predict regional apple production to inform and develop national planting policies, agricultural management, and export strategies.

[1]  Pablo J. Zarco-Tejada,et al.  Monitoring yield and fruit quality parameters in open-canopy tree crops under water stress. Implications for ASTER , 2007 .

[2]  Gengxing Zhao,et al.  Improving the Accuracy of the Hyperspectral Model for Apple Canopy Water Content Prediction using the Equidistant Sampling Method , 2017, Scientific Reports.

[3]  C. Justice,et al.  Development of vegetation and soil indices for MODIS-EOS , 1994 .

[4]  Lingling Fan,et al.  Identification of Apple Orchard Planting Year Based on Spatiotemporally Fused Satellite Images and Clustering Analysis of Foliage Phenophase , 2020, Remote. Sens..

[5]  Guijun Yang,et al.  Hyperspectral Estimation of Apple Canopy Chlorophyll Content Using an Ensemble Learning Approach , 2021 .

[6]  A. Gowen,et al.  Prediction of polyphenol oxidase activity using visible near-infrared hyperspectral imaging on mushroom (Agaricus bisporus) caps. , 2010, Journal of agricultural and food chemistry.

[7]  Deren Li,et al.  A review of vegetation phenological metrics extraction using time-series, multispectral satellite data , 2020 .

[8]  Lingling Fan,et al.  An Improved CASA Model for Estimating Winter Wheat Yield from Remote Sensing Images , 2019, Remote. Sens..

[9]  M. A. Asoodar,et al.  Evaluation of sum-NDVI values to estimate wheat grain yields using multi-temporal Landsat OLI data , 2019, Geocarto International.

[10]  T. Vesala,et al.  Deriving a light use efficiency model from eddy covariance flux data for predicting daily gross primary production across biomes , 2007 .

[11]  Qiangzi Li,et al.  Winter wheat biomass estimation using high temporal and spatial resolution satellite data combined with a light use efficiency model , 2015 .

[12]  Guangsheng Zhou,et al.  Light Use Efficiency over Two Temperate Steppes in Inner Mongolia, China , 2012, PloS one.

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

[14]  Lailiang Cheng,et al.  Developmental changes of carbohydrates, organic acids, amino acids, and phenolic compounds in 'Honeycrisp' apple flesh. , 2010 .

[15]  Chi-Farn Chen,et al.  Machine learning approaches for rice crop yield predictions using time-series satellite data in Taiwan , 2020 .

[16]  Shujing Cao,et al.  Estimating apple tree canopy chlorophyll content based on Sentinel-2A remote sensing imaging , 2018, Scientific Reports.

[17]  J. Roujean,et al.  Estimating PAR absorbed by vegetation from bidirectional reflectance measurements , 1995 .

[18]  D. Bochtis,et al.  Yield prediction in apple orchards based on image processing , 2011, Precision Agriculture.

[19]  R. Linker.  Machine learning based analysis of night-time images for yield prediction in apple orchard , 2018 .

[20]  Chao Chen,et al.  Fruit Detection and Segmentation for Apple Harvesting Using Visual Sensor in Orchards , 2019, Sensors.

[21]  M. Trnka,et al.  Simulation of winter wheat yield and its variability in different climates of Europe: A comparison of eight crop growth models , 2011 .

[22]  Douglas K. Bolton,et al.  Forecasting crop yield using remotely sensed vegetation indices and crop phenology metrics , 2013 .

[23]  S. Running,et al.  Global Terrestrial Gross and Net Primary Productivity from the Earth Observing System , 2000 .

[24]  Laurent Tits,et al.  Temporal Dependency of Yield and Quality Estimation through Spectral Vegetation Indices in Pear Orchards , 2015, Remote. Sens..

[25]  Qingyun Du,et al.  Alfalfa Yield Prediction Using UAV-Based Hyperspectral Imagery and Ensemble Learning , 2020, Remote. Sens..

[26]  Weixing Cao,et al.  Predicting grain yield and protein content in wheat by fusing multi-sensor and multi-temporal remote-sensing images , 2014 .

[27]  P. Heuberger,et al.  Calibration of process-oriented models , 1995 .

[28]  Kenshi Sakai,et al.  Estimation of citrus yield from canopy spectral features determined by airborne hyperspectral imagery , 2009 .

[29]  Mohsen Shahhosseini,et al.  Forecasting Corn Yield With Machine Learning Ensembles , 2020, Frontiers in Plant Science.

[30]  Tao Wang,et al.  Assimilation of Remotely-Sensed LAI into WOFOST Model with the SUBPLEX Algorithm for Improving the Field-Scale Jujube Yield Forecasts , 2019, Remote. Sens..

[31]  Bin Xing,et al.  A smartphone-based apple yield estimation application using imaging features and the ANN method in mature period , 2018 .

[32]  Nannan Zhang,et al.  Jujube yield prediction method combining Landsat 8 Vegetation Index and the phenological length , 2019, Comput. Electron. Agric..

[33]  Kenshi Sakai,et al.  Prediction of citrus yield from airborne hyperspectral imagery , 2007, Precision Agriculture.

[34]  Maite Loidi,et al.  Sampling Stratification Using Aerial Imagery to Estimate Fruit Load in Peach Tree Orchards , 2018, Agriculture.

[35]  H. Bergamaschi,et al.  Solar radiation effects on growth, anatomy, and physiology of apple trees in a temperate climate of Brazil , 2020, International Journal of Biometeorology.

[36]  Andrew Robson,et al.  Exploring the Potential of High Resolution WorldView-3 Imagery for Estimating Yield of Mango , 2018, Remote. Sens..

[37]  Flavio Esposito,et al.  Soybean yield prediction from UAV using multimodal data fusion and deep learning , 2020 .

[38]  Y. Bao,et al.  Modifying the maximal light-use efficiency for enhancing predictions of vegetation net primary productivity on the Mongolian Plateau , 2020 .

[39]  Andrew Robson,et al.  Using Worldview Satellite Imagery to Map Yield in Avocado (Persea americana): A Case Study in Bundaberg, Australia , 2017, Remote. Sens..

[40]  Ahmad Khan,et al.  Wheat Yield Forecasting for Punjab Province from Vegetation Index Time Series and Historic Crop Statistics , 2014, Remote. Sens..

[41]  S. Güler.  Effects of nitrogen on yield and chlorophyll of potato (Solanum tuberosum L.) cultivars. , 2010 .

[42]  C. Diao.  Remote sensing phenological monitoring framework to characterize corn and soybean physiological growing stages , 2020 .

[43]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .

[44]  Andrew Davidson,et al.  Assessing the Performance of MODIS NDVI and EVI for Seasonal Crop Yield Forecasting at the Ecodistrict Scale , 2014, Remote. Sens..

[45]  R. Zhou,et al.  Using colour features of cv. ‘Gala’ apple fruits in an orchard in image processing to predict yield , 2012, Precision Agriculture.

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

[47]  Shusen Wang,et al.  Crop yield forecasting on the Canadian Prairies using MODIS NDVI data , 2011 .

[48]  R. Fieuzal,et al.  Combined Use of Multi-Temporal Landsat-8 and Sentinel-2 Images for Wheat Yield Estimates at the Intra-Plot Spatial Scale , 2020 .

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

[50]  E. D. Quicho,et al.  Rice yield estimation using synthetic aperture radar (SAR) and the ORYZA crop growth model: development and application of the system in South and South-east Asian countries , 2018, International Journal of Remote Sensing.

[51]  Josse De Baerdemaeker,et al.  Comparison of an aerial-based system and an on the ground continuous measuring device to predict yield of winter wheat , 2006 .

[52]  Nengcheng Chen,et al.  Using Multi-Temporal MODIS NDVI Data to Monitor Tea Status and Forecast Yield: A Case Study at Tanuyen, Laichau, Vietnam , 2020, Remote. Sens..