Combining machine learning and remote sensing-integrated crop modeling for rice and soybean crop simulation.

Machine learning (ML) techniques offer a promising avenue for improving the integration of remote sensing data into mathematical crop models, thereby enhancing crop growth prediction accuracy. A critical variable for this integration is the leaf area index (LAI), which can be accurately assessed using proximal or remote sensing data based on plant canopies. This study aimed to (1) develop a machine learning-based method for estimating the LAI in rice and soybean crops using proximal sensing data and (2) evaluate the performance of a Remote Sensing-Integrated Crop Model (RSCM) when integrated with the ML algorithms. To achieve these objectives, we analyzed rice and soybean datasets to identify the most effective ML algorithms for modeling the relationship between LAI and vegetation indices derived from canopy reflectance measurements. Our analyses employed a variety of ML regression models, including ridge, lasso, support vector machine, random forest, and extra trees. Among these, the extra trees regression model demonstrated the best performance, achieving test scores of 0.86 and 0.89 for rice and soybean crops, respectively. This model closely replicated observed LAI values under different nitrogen treatments, achieving Nash-Sutcliffe efficiencies of 0.93 for rice and 0.97 for soybean. Our findings show that incorporating ML techniques into RSCM effectively captures seasonal LAI variations across diverse field management practices, offering significant potential for improving crop growth and productivity monitoring.

Development of a Soil Moisture Prediction Model Based on Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) in Soybean Cultivation.

Due to climate change, soil moisture may increase, and outflows could become more frequent, which will have a considerable impact on crop growth. Crops are affected by soil moisture; thus, soil moisture prediction is necessary for irrigating at an appropriate time according to weather changes. Therefore, the aim of this study is to develop a future soil moisture (SM) prediction model to determine whether to conduct irrigation according to changes in soil moisture due to weather conditions. Sensors were used to measure soil moisture and soil temperature at a depth of 10 cm, 20 cm, and 30 cm from the topsoil. The combination of optimal variables was investigated using soil moisture and soil temperature at depths between 10 cm and 30 cm and weather data as input variables. The recurrent neural network long short-term memory (RNN-LSTM) models for predicting SM was developed using time series data. The loss and the coefficient of determination (R2) values were used as indicators for evaluating the model performance and two verification datasets were used to test various conditions. The best model performance for 10 cm depth was an R2 of 0.999, a loss of 0.022, and a validation loss of 0.105, and the best results for 20 cm and 30 cm depths were an R2 of 0.999, a loss of 0.016, and a validation loss of 0.098 and an R2 of 0.956, a loss of 0.057, and a validation loss of 2.883, respectively. The RNN-LSTM model was used to confirm the SM predictability in soybean arable land and could be applied to supply the appropriate moisture needed for crop growth. The results of this study show that a soil moisture prediction model based on time-series weather data can help determine the appropriate amount of irrigation required for crop cultivation.

Comparison of Gene Expression Changes in Three Wheat Varieties with Different Susceptibilities to Heat Stress Using RNA-Seq Analysis.

Wheat is highly susceptible to heat stress, which significantly reduces grain yield. In this study, we used RNA-seq technology to analyze the transcript expression at three different time-points after heat treatment in three cultivars differing in their susceptibility to heat stress: Jopum, Keumkang, and Olgeuru. A total of 11,751, 8850, and 14,711; 10,959, 7946, and 14,205; and 22,895, 13,060, and 19,408 differentially-expressed genes (log2 fold-change > 1 and FDR (padj) < 0.05) were identified in Jopum, Keumkang, and Olgeuru in the control vs. 6-h, in the control vs. 12-h, and in the 6-h vs. 12-h heat treatment, respectively. Functional enrichment analysis showed that the biological processes for DEGs, such as the cellular response to heat and oxidative stress­and including the removal of superoxide radicals and the positive regulation of superoxide dismutase activity­were significantly enriched among the three comparisons in all three cultivars. Furthermore, we investigated the differential expression patterns of reactive oxygen species (ROS)-scavenging enzymes, heat shock proteins, and heat-stress transcription factors using qRT-PCR to confirm the differences in gene expression among the three varieties under heat stress. This study contributes to a better understanding of the wheat heat-stress response at the early growth stage and the varietal differences in heat tolerance.

The effect of concurrent elevation in CO2 and temperature on the growth, photosynthesis, and yield of potato crops.

Global climate change accompanied by continuous increases in atmospheric carbon dioxide (CO2) concentration and temperature affects the growth and yield of important crops. The present study investigated the effect of elevated temperature and CO2 concentrations on the growth, yield, and photosynthesis of potato (Solanum tuberosum L. cv. Superior) crops using Korean Soil-Plant-Atmosphere-Research chambers that allow the regulation of temperature and CO2 concentration under daylight conditions. Based on the average temperature from 1991 to 2010 in the Jeonju area, South Korea, potato plants were exposed to four different conditions: ambient weather (400 µmol mol-1, aCaT), elevated temperature (+4°C, aCeT), elevated CO2 concentration (800 µmol mol-1, eCaT), and concurrently elevated CO2 concentration and temperature (eCeT). Under aCeT conditions, the temperature exceeded the optimal growth temperature range towards the late growth phase that decreased stomatal conductance and canopy net photosynthetic rate and subsequently reduced biomass and tuber yield. Stomatal conductance and chlorophyll concentration were lower under eCaT conditions than under aCaT conditions, whereas late-growth phase biomass and tuber yield were greater. Compared to other conditions, eCeT yielded a distinct increase in growth and development and canopy net photosynthetic rate during tuber initiation and bulking. Consequently, biomass and canopy net photosynthesis increased, and tuber yield increased by 20.3%, which could be attributed to the increased tuber size, rather than increased tuber number. Elevated CO2 reduced chlorophyll, magnesium, and phosphorus concentrations; reducing nitrogen concentration (by approximately 39.7%) increased the C:N ratio. The data indicate that future climate conditions will likely change nutrient concentration and quality of crops. The present study shows that while elevated temperature may negatively influence the growth and yield of potato crops, especially towards the late-growth phase, the concurrent and appropriate elevation of CO2 and temperature could promote balanced development of source and sink organs and positively effect potato productivity and quality.