Incorporation of machine learning and deep neural network approaches into a remote sensing-integrated crop model for the simulation of rice growth.

Machine learning (ML) and deep neural network (DNN) techniques are promising tools. These can advance mathematical crop modelling methodologies that can integrate these schemes into a process-based crop model capable of reproducing or simulating crop growth. In this study, an innovative hybrid approach for estimating the leaf area index (LAI) of paddy rice using climate data was developed using ML and DNN regression methodologies. First, we investigated suitable ML regressors to explore the LAI estimation of rice based on the relationship between the LAI and three climate factors in two administrative rice-growing regions of South Korea. We found that of the 10 ML regressors explored, the random forest regressor was the most effective LAI estimator, and it even outperformed the DNN regressor, with model efficiencies of 0.88 in Cheorwon and 0.82 in Paju. In addition, we demonstrated that it would be feasible to simulate the LAI using climate factors based on the integration of the ML and DNN regressors in a process-based crop model. Therefore, we assume that the advancements presented in this study can enhance crop growth and productivity monitoring practices by incorporating a crop model with ML and DNN plans.

Predicting rice yield at pixel scale through synthetic use of crop and deep learning models with satellite data in South and North Korea.

Prediction of rice yields at pixel scale rather than county scale can benefit crop management and scientific understanding because it is useful for monitoring how crop yields respond to various agricultural systems and environmental factors. In this study, we propose a methodology for the early prediction of rice yield at pixel scale combining a crop model and a deep learning model for different agricultural systems throughout South and North Korea. Initially, satellite-integrated crop models were applied to obtain a pixel-scale reference rice yield. Then, the pixel-scale reference rice yields were used as target labels in the deep learning model to leverage the advantages of crop models. Models of five different deep learning network architectures were employed to help determine the hybrid structure of long-short term memory (LSTM) and one-dimensional convolutional neural network (1D-CNN) layers by predicting the optimal model about two months ahead of harvest time. The suggested model showed good performance [R2 = 0.859, Nash-Sutcliffe model efficiency = 0.858, root mean squared error = 0.605 Mg ha-1], with specific spatial patterns of rice yields for South and North Korea. Analysis of the relative importance of the input variables showed the water-related index and maximum temperature in North Korea and the vegetation indices and geographic variables in South Korea to be crucial for predicting rice yields. The proposed approach successfully predicted and diagnosed rice yield at the pixel scale for inaccessible locations where reliable ground measurements are not available, especially North Korea.

Simulation of Wheat Productivity Using a Model Integrated With Proximal and Remotely Controlled Aerial Sensing Information.

A crop model incorporating proximal sensing images from a remote-controlled aerial system (RAS) can serve as an enhanced alternative for monitoring field-based geospatial crop productivity. This study aimed to investigate wheat productivity for different cultivars and various nitrogen application regimes and determine the best management practice scenario. We simulated spatiotemporal wheat growth and yield by integrating RAS-based sensing images with a crop-modeling system to achieve the study objective. We conducted field experiments and proximal sensing campaigns to acquire the ground truth data and RAS images of wheat growth conditions and yields. These experiments were performed at Gyeongsang National University (GNU), Jinju, South Gyeongsang province, Republic of Korea (ROK), in 2018 and 2019 and at Chonnam National University (CNU), Gwangju, ROK, in 2018. During the calibration at GNU in 2018, the wheat yields simulated by the modeling system were in agreement with the corresponding measured yields without significant differences (p = 0.27-0.91), according to two-sample t-tests. Furthermore, the yields simulated via this approach were in agreement with the measured yields at CNU in 2018 and at GNU in 2019 without significant differences (p = 0.28-0.86), as evidenced by two-sample t-tests; this proved the validity of the proposed modeling system. This system, when integrated with remotely sensed images, could also accurately reproduce the geospatial variations in wheat yield and growth variables. Given the results of this study, we believe that the proposed crop-modeling approach is applicable for the practical monitoring of wheat growth and productivity at the field level.

Geographical variations in gross primary production and evapotranspiration of paddy rice in the Korean Peninsula.

The quantification of canopy photosynthesis and evapotranspiration of crops (ETc) is essential to appreciate the effects of environmental changes on CO2 flux and water availability in agricultural ecosystems and crop productivity. This study simulated the canopy photosynthesis and ET processes of paddy rice (Oryza sativa) based on the development of physiological modules (i.e., gross primary production [GPP] and ETc) and their incorporation into the GRAMI-rice model that uses remote sensing data. We also projected spatiotemporal variations in the GPP, ET, yield, and biomass of paddy rice at maturity using the updated GRAMI-rice model combined with geostationary satellite images to identify the relationships of canopy photosynthesis and ETc with crop productivity. GPP and ET data for paddy rice were obtained from three KoFlux sites in South Korea in 2015 and 2016. Vegetation indices were acquired from the Geostationary Ocean Color Imager (GOCI) of the Communication Ocean and Meteorological Satellite (COMS) from 2012 to 2017 and integrated into GRAMI-rice. GPP and ETc estimates using GRAMI-rice were in close agreement with flux tower estimates with Nash-Sutcliffe efficiency ranges of 0.40-0.79 for GPP and 0.49-0.62 for ETc. Also, GRAMI-rice was reasonably well incorporated with the COMS GOCI imagery and reproduced spatiotemporal variations in the GPP and ET of rice in the Korean peninsula. The current study results demonstrate that the updated GRAMI-rice model with the canopy photosynthesis and ETc modules is capable of reproducing spatiotemporal variations in CO2 assimilation and ET of paddy rice at various geographical scales and for regions of interest that are observable by satellite sensors (e.g., inaccessible North Korea).

Monitoring paddy productivity in North Korea employing geostationary satellite images integrated with GRAMI-rice model.

To meet the growing demands of staple crops with a strategy to develop amicable strategic measures that support efficient North Korean relief policies, it is a desirable task to accurately simulate the yield of paddy (Oryza sativa), an important Asian food commodity. We aim to address this with a grid-based crop simulation model integrated with satellite imagery that enables us to monitor the crop productivity of North Korea. Vegetation Indices (VIs), solar insolation, and air temperature data are thus obtained from the Communication Ocean and Meteorological Satellite (COMS), including the reanalysis data of the Korea Local Analysis and Prediction System (KLAPS). Paddy productivities for North Korea are projected based on the bidirectional reflectance distribution function-adjusted VIs and the solar insolation using the grid GRAMI-rice model. The model is calibrated on a 500-m grid paddy field in Cheorwon, and the model simulation performance accuracy is verified for Cheorwon and Paju, located at the borders of North Korea using four years of data from 2011 to 2014. Our results show that the paddy yields are reproduced reasonably accurately within a statistically significant range of accuracy, in comparison with observation data in Cheorwon (p = 0.183), Paju (p = 0.075), and NK (p = 0.101) according to a statistical t-test procedure. We advocate that incorporating a crop model with satellite images for crop yield simulations can be utilised as a reliable estimation technique for the monitoring of crop productivity, particularly in unapproachable, data-sparse regions not only in North Korea, but globally, where estimations of paddy productivity can assist in planning of agricultural activities that support regionally amicable food security strategies.