Using Multi-Temporal MODIS NDVI Data to Monitor Tea Status and Forecast Yield: A Case Study at Tanuyen, Laichau, Vietnam

Abstract

Tea is a cash crop that improves the quality of life for people in the Tanuyen District of Laichau Province, Vietnam. Tea yield, however, has stagnated in recent years, due to changes in temperature, precipitation, the age of the tea bushes, and diseases. Developing an approach for monitoring tea bushes by remote sensing and Geographic Information Systems (GIS) might be a way to alleviate this problem. Using multi-temporal remote sensing data, the paper details an investigation of the changes in tea health and yield forecasting through the normalized difference vegetation index (NDVI). In this study, we used NDVI as a support tool to demonstrate the temporal and spatial changes in NDVI through the extract tea NDVI value and calculate the mean NDVI value. The results of the study showed that the minimum NDVI value was 0.42 during January 2013 and February 2015 and 2016. The maximum NDVI value was in August 2015 and June 2017. We indicate that the linear relationship between NDVI value and mean temperature was strong with R 2 = 0.79 Our results confirm that the combination of meteorological data and NDVI data can achieve a high performance of yield prediction. Three models to predict tea yield were conducted: support vector machine (SVM), random forest (RF), and the traditional linear regression model (TLRM). For period 2009 to 2018, the prediction tea yield by the RF model was the best with a R 2 = 0.73 , by SVM it was 0.66, and 0.57 with the TLRM. Three evaluation indicators were used to consider accuracy: the coefficient of determination ( R 2 ), root-mean-square error (RMSE), and percentage error of tea yield (PETY). The highest accuracy for the three models was in 2015 with a R 2 ≥ 0.87, RMSE < 50 kg/ha, and PETY less 3% error. In the other years, the prediction accuracy was higher in the SVM and RF models. Meanwhile, the RF algorithm was better than PETY (≤10%) and the root mean square error for this algorithm was significantly less (≤80 kg/ha). RMSE and PETY showed relatively good values in the TLRM model with a RMSE from 80 to 100 kg/ha and a PETY from 8 to 15%.

Application of Machine Learning Algorithms in Plant Breeding: Predicting Yield From Hyperspectral Reflectance in Soybean

“…The visible reflectance bands can be splitted into three main regions, red (650–700 nm), green (495–570 nm), and violet–blue (390–495 nm) ( Hennessy et al, 2020 ). Most studies were emphasized the importance of red spectral bands or the combined use of red and red edge bands as one solid index in predicting the total yield ( Jolly et al, 2005 ; Filippa et al, 2018 ; Lykhovyd, 2020 ; Phan et al, 2020 ; Tiwari and Shukla, 2020 ). In this study, we identified highly ranked bands in the violet and red regions for classifying the soybean seed yield, centered at 395 nm, 665 nm, and 675 nm ( Table 2 ).…”

Mapping tea plantations dynamics during 2000–2020 and monitoring biophysical attributes using multi-temporal satellite data in North Bengal (India)

“…The aforementioned biophysical and biochemical attributes are strongly connected to the overall health conditions of vegetation (Marandi et al 2021;Phan et al 2020), including tea plantations and productivity. However, other environmental variables (rainfall, temperature, relative humidity, solar radiation, and soil moisture), extreme weather conditions (i.e., drought, floods, and heatwaves), and climate variability (e.g., ENSO) also determine the productivity of tea (Ahmed et al 2014;Raj et al 2020).…”

“…West Bengal produces tea mainly from Darjeeling, Dooars (Jalpaiguri), and Terai (North Dinajpur) regions, contributing nearly 24% of the total production of India (Tea Board of India 2018). Tea usually does not compete with food crops and hence, tea plantations are mostly found over bare land and bare hills (Phan et al 2020).…”

NDVI Variation and Yield Prediction in Growing Season: A Case Study with Tea in Tanuyen Vietnam

“…where R xy is the Pearson correlation coefficients for x and y variable which have value from −1 to 1. x i is NDVI value in the ith month [38], y i is the mean monthly climate factor in the ith month [24] and x y are the average of x and y, respectively.…”

“…From a large number of individual trees generated, they voted the most popular classes. Many research showed that RF may reach the best predictive performances compared to other methodologies [38,45,46].…”