• Journal of Bio-Environment Control
• /
• v.32 no.4
• /
• pp.384-395
• /
• 2023

Since transpiration plays a key role in optimal irrigation management, knowledge of the irrigation demand of crops like tomatoes, which are highly susceptible to water stress, is necessary. One way to determine irrigation demand is to measure transpiration, which is affected by environmental factor or growth stage. This study aimed to estimate the transpiration amount of tomatoes and find a suitable model using mathematical and deep learning models using minute-by-minute data. Pearson correlation revealed that observed environmental variables significantly correlate with crop transpiration. Inside air temperature and outside radiation positively correlated with transpiration, while humidity showed a negative correlation. Multiple Linear Regression (MLR), Polynomial Regression model, Artificial Neural Network (ANN), Long short-term Memory (LSTM), and Gated Recurrent Unit (GRU) models were built and compared their accuracies. All models showed potential in estimating transpiration with R² values ranging from 0.770 to 0.948 and RMSE of 0.495 mm/min to 1.038 mm/min in the test dataset. Deep learning models outperformed the mathematical models; the GRU demonstrated the best performance in the test data with 0.948 R² and 0.495 mm/min RMSE. The LSTM and ANN closely followed with R² values of 0.946 and 0.944, respectively, and RMSE of 0.504 m/min and 0.511, respectively. The GRU model exhibited superior performance in short-term forecasts while LSTM for long-term but requires verification using a large dataset. Compared to the FAO56 Penman-Monteith (PM) equation, PM has a lower RMSE of 0.598 mm/min than MLR and Polynomial models degrees 2 and 3 but performed least among all models in capturing variability in transpiration. Therefore, this study recommended GRU and LSTM models for short-term estimation of tomato transpiration in greenhouses.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.36 no.5
• /
• pp.407-428
• /
• 1991

The eastern coastal area having variability of climate is located within Taebaek mountain range and the east coast of Korea. It is therefore ease to cause the wind damages in paddy field during rice growing season. The wind damages to rice plant in this area were mainly caused by the Fohn wind (dry and hot wind) blowing over the Taebaek mountain range and the cold humid wind from the coast. The dry wind cause such as the white head, broken leaves, cut-leaves, dried leaves, shattering of grain, glume discolouration and lodging, On the other hand the cold humid wind derived from Ootsuku air mass in summer cause such symptom as the poor rice growth, degeneration of rachis brenches and poor ripening. To minimize the wind damages and utilize as a preparatory data for wind injury of rice in future, several experiments such as the selection of wind resistant variety to wind damage, determination of optimum transplanting date, improvement of fertilizer application methods, improvement of soils and effect of wind break net were carried out for 8 years from 1982 to 1989 in the eastern coastal area. The results obtained are summarized as follows. 1. According to available statisical data from Korean meteorological services (1954-1989) it is apperent that cold humid winds frequently cause damage to rice fields from August 10th to September 10th, it is therefore advisable to plan rice cultivation in such a way that the heading date should not be later than August 10th. 2. During the rice production season, two winds cause severe damage to the rice fields in eastern coastal area of Korea. One is the Fohn winds blowing over the Taebaek mountain range and the other is the cold humid wind form the coast. The frequency of occurrence of each wind was 25%. 3. To avoid damage caused by typhoon winds three different varieties of rice were planted at various areas. 4. In the eastern coastal area of Korea, the optimum ripening temperature for rice was about 22.2$^{\circ}C$ and the optimum heading date wad August 10th. The optimum transplanting time for the earily maturity variety was June 10th., medium maturity variety was May 20th and that of late maturity was May 10th by means of growing days degree (GDD) from transplanting date to heading date. 5.38% of this coastal area is sandy loamy soil while 28% is high humus soil. These soil types are very poor for rice cultivation. In this coastal area, the water table is high, the drainage is poor and the water temperature is low. The low water temperature makes it difficult for urea to dissolve, as a result rice growth was delayed, and the rice plant became sterile. But over application of urea resulted in blast disease in rice plants. It is therefore advise that Ammonium sulphate is used in this area instead of urea. 6. The low temperature of the soil inhibits activities of microorganism for phosphorus utilization so the rice plant could not easily absorb the phosphorus in the soil. Therefore phosphorus should be applied in splits from transplanting to panicle initiation rather than based application. 7. Wind damage was severe in the sandy loamy soil as compared to clay soils. With the application of silicate. compost and soil from mointain area. the sand loamy soil was improved for rice grain colour and ripening. 8. The use of wind break nets created a mocro-climate such as increased air. soil and water temperature as well as the reduction of wind velocity by 30%. This hastened rice growth, reduced white head and glume discolouration. improved rice quality and increased yield. 9. Two meter high wind break net was used around the rice experimental fields and the top of it. The material was polyethylene sheets. The optimum spacing was 0.5Cm x 0.5Cm. and that of setting up the wind break net was before panicle initiation. With this set up, the field was avoided off th cold humid wind and the Fohn. The yield in the treatment was 20% higher than the control. 10. After typhoon, paddy field was irrigated deeply and water was sprayed to reduce white head, glume discolouration, so rice yield was increased because of increasing ripening ratio and 1, 000 grain weight.