Application of Optical Remote Sensing in Rubber Plantations: A Systematic Review

Object-oriented multi-scale segmentation and multi-feature fusion-based method for identifying typical fruit trees in arid regions using Sentinel-1/2 satellite images

Fruit tree identification that is quick and precise lays the groundwork for scientifically evaluating orchard yields and dynamically monitoring planting areas. This study aims to evaluate the applicability of time series Sentinel-1/2 satellite data for fruit tree classification and to provide a new method for accurately extracting fruit tree species. Therefore, the study area selected is the Tarim Basin, the most important fruit-growing region in northwest China. The main focus is on identifying several major fruit tree species in this region. Time series Sentinel-1/2 satellite images acquired from the Google Earth Engine (GEE) platform are used for the study. A multi-scale segmentation approach is applied, and six categories of features including spectral, phenological, texture, polarization, vegetation index, and red edge index features are constructed. A total of forth-four features are extracted and optimized using the Vi feature importance index to determine the best time phase. Based on this, an object-oriented (OO) segmentation combined with the Random Forest (RF) method is used to identify fruit tree species. To find the best method for fruit tree identification, the results are compared with three other widely used traditional machine learning algorithms: Support Vector Machine (SVM), Gradient Boosting Decision Tree (GBDT), and Classification and Regression Tree (CART). The results show that: (1) the object-oriented segmentation method helps to improve the accuracy of fruit tree identification features, and September satellite images provide the best time window for fruit tree identification, with spectral, phenological, and texture features contributing the most to fruit tree species identification. (2) The RF model has higher accuracy in identifying fruit tree species than other machine learning models, with an overall accuracy (OA) and a kappa coefficient (KC) of 94.60% and 93.74% respectively, indicating that the combination of object-oriented segmentation and RF algorithm has great value and potential for fruit tree identification and classification. This method can be applied to large-scale fruit tree remote sensing classification and provides an effective technical means for monitoring fruit tree planting areas using medium-to-high-resolution remote sensing images.

Dry season temperature and rainy season precipitation significantly affect the spatio-temporal pattern of rubber plantation phenology in Yunnan province

The ongoing global warming trajectory poses extensive challenges to plant ecosystems, with rubber plantations particularly vulnerable due to their influence on not only the longevity of the growth cycle and rubber yield, but also the complex interplay of carbon, water, and energy exchanges between the forest canopy and atmosphere. However, the response mechanism of phenology in rubber plantations to climate change remains unclear. This study concentrates on sub-optimal environment rubber plantations in Yunnan province, Southwest China. Utilizing the Google Earth Engine (GEE) cloud platform, multi-source remote sensing images were synthesized at 8-day intervals with a spatial resolution of 30-meters. The Normalized Difference Vegetation Index (NDVI) time series was reconstructed using the Savitzky-Golay (S-G) filter, coupled with the application of the seasonal amplitude method to extract three crucial phenological indicators, namely the start of the growing season (SOS), the end of the growing season (EOS), and the length of the growing season (LOS). Linear regression method, Pearson correlation coefficient, multiple stepwise regression analysis were used to extract of the phenology trend and find the relationship between SOS, EOS and climate factors. The findings demonstrated that 1) the phenology of rubber plantations has undergone dynamic changes over the past two decades. Specifically, the SOS advanced by 9.4 days per decade (R2 = 0.42, p< 0.01), whereas the EOS was delayed by 3.8 days per decade (R2 = 0.35, p< 0.01). Additionally, the LOS was extended by 13.2 days per decade (R2 = 0.55, p< 0.01); 2) rubber phenology demonstrated a notable sensitivity to temperature fluctuations during the dry season and precipitation patterns during the rainy season. The SOS advanced 2.0 days (r =-0.19, p< 0.01) and the EOS advanced 2.8 days (r =-0.35, p< 0.01) for every 1°C increase in the cool-dry season. Whereas a 100 mm increase in rainy season precipitation caused the SOS to be delayed by 2.0 days (r = 0.24, p< 0.01), a 100 mm increase in hot-dry season precipitation caused the EOS to be advanced by 7.0 days (r =-0.28, p< 0.01); 3) rubber phenology displayed a legacy effect of preseason climate variations. Changes in temperature during the fourth preseason month and precipitation during the fourth and eleventh preseason months are predominantly responsible for the variation in SOS. Meanwhile, temperature changes during the second, fourth, and ninth preseason months are primarily responsible for the variation in EOS. The study aims to enhance our understanding of how rubber plantations respond to climate change in sub-optimal environments and provide valuable insights for sustainable rubber production management in the face of changing environmental conditions.

Painting Classification in Art Teaching under Machine Learning from the Perspective of Emotional Semantic Analysis

This paper aims to explore the Painting Classification in art teaching under Machine Learning. Based on Emotional Semantics and Machine Learning, the Emotional Semantics of the traditional image are expounded. Firstly, Emotional Semantics are applied to figure painting in art teaching. Then, the convolutional sparse automatic encoder model is introduced in Painting Classification. Finally, the accuracies of the Painting Classification of the Support Vector Machine classifier (SVMC) and that of the Naive Bayes classifier are compared, and the relevant conclusions are drawn. The accuracy of Painting Classification is positively correlated with the scale of painting. After analysis, the painting set is classified in a ratio of 2 : 1, with 2/3 as training set and 1/3 as test set, which is conducive to the good accuracy of classification. In Machine Learning, proper whitening can improve the accuracy of Painting Classification to a certain extent. However, when the whitening treatment coefficient is selected, it cannot be too large, and the average pooling is more accurate than maximum pooling. After the comparison of the new SVMC, the Naive Bayes classifier, and the convolutional sparse automatic encoder, the convolutional sparse automatic encoder has the highest accuracy of Painting Classification. Therefore, the Painting Classification in art teaching under Machine Learning is explored, which is of great help to the classification work of students or teachers in the future.

The Suitability of PlanetScope Imagery for Mapping Rubber Plantations

Quickly and accurately understanding the spatial distribution of regional rubber resources is of great practical significance. Using the unique phenological characteristics of rubber trees derived from remotely sensed data is a common effective method for monitoring rubber trees. However, due to the lack of high-quality images available during the key phenological period, it is still very difficult to apply this method in practical applications. PlanetScope data with high temporal (daily) resolution have great advantages in acquiring high-quality images, but these images have not been previously used to monitor rubber plantations. In this paper, multitemporal PlanetScope images were used as data sources, and the spectral features, index features, first principal components, and textural features of the images were comprehensively utilized. Four classification methods, including a pixel-based random forest (RF) approach, pixel-based support vector machine (SVM) approach, object-oriented RF approach and object-oriented SVM approach, were utilized to discuss the feasibility of using PlanetScope data to monitor rubber forests. The results showed that the optimal time window for monitoring rubber forests in the study area spanned from the 49th day to the 65th day of 2019 according to the MODIS-NDVI analysis. The contribution rate of the difference in the modified simple ratio (dMSR) feature was largest among all considered features for all pixel-based and object-oriented methods. The object-oriented RF/SVM classification method achieved the best classification results with an overall accuracy of 93.87% and a Kappa index of agreement (KIA) of 0.92. The highest producer’s accuracy and user’s accuracy obtained with this method were 95.18% for rubber plantations. The results of this study show that it is feasible to use PlanetScope data to perform rubber monitoring, thus effectively solving the problem of missing images in the optimal rubber monitoring period; additionally, this method can be extended to other real-life applications.

Using Multi-Temporal Satellite Data to Analyse Phenological Responses of Rubber (Hevea brasiliensis) to Climatic Variations in South Sumatra, Indonesia

Land surface phenology derived from satellite data provides insights into vegetation responses to climate change. This method has overcome laborious and time-consuming manual ground observation methods. In this study, we assessed the influence of climate on phenological metrics of rubber (Hevea brasiliensis) in South Sumatra, Indonesia, between 2010 and 2019. We modelled rubber growth through the normalised difference vegetation index (NDVI), using eight-day surface reflectance images at 250 m spatial resolution, sourced from NASA’s Moderate Resolution Imaging Spectroradiometer (MODIS) Terra and Aqua satellites. The asymmetric Gaussian (AG) smoothing function was applied on the model in TIMESAT to extract three phenological metrics for each growing season: start of season (SOS), end of season (EOS), and length of season (LOS). We then analysed the effect of rainfall and temperature, which revealed that fluctuations in SOS and EOS are highly related to disturbances such as extreme rainfall and elevated temperature. Additionally, we observed inter-annual variations of SOS and EOS associated with rubber tree age and clonal variability within plantations. The 10-year monthly climate data showed a significant downward and upward trend for rainfall and temperature data, respectively. Temperature was identified as a significant factor modulating rubber phenology, where an increase in temperature of 1 °C advanced SOS by ~25 days and EOS by ~14 days. These results demonstrate the capability of remote sensing observations to monitor the effects of climate change on rubber phenology. This information can be used to improve rubber management by helping to identify critical timing for implementation of agronomic interventions.

Integrating Phenological and Geographical Information with Artificial Intelligence Algorithm to Map Rubber Plantations in Xishuangbanna

Most natural rubber trees (Hevea brasiliensis) are grown on plantations, making rubber an important industrial crop. Rubber plantations are also an important source of household income for over 20 million people. The accurate mapping of rubber plantations is important for both local governments and the global market. Remote sensing has been a widely used approach for mapping rubber plantations, typically using optical remote sensing data obtained at the regional scale. Improving the efficiency and accuracy of rubber plantation maps has become a research hotspot in rubber-related literature. To improve the classification efficiency, researchers have combined the phenology, geography, and texture of rubber trees with spectral information. Among these, there are three main classifiers: maximum likelihood, QUEST decision tree, and random forest methods. However, until now, no comparative studies have been conducted for the above three classifiers. Therefore, in this study, we evaluated the mapping accuracy based on these three classifiers, using four kinds of data input: Landsat spectral information, phenology–Landsat spectral information, topography–Landsat spectral information, and phenology–topography–Landsat spectral information. We found that the random forest method had the highest mapping accuracy when compared with the maximum likelihood and QUEST decision tree methods. We also found that adding either phenology or topography could improve the mapping accuracy for rubber plantations. When either phenology or topography were added as parameters within the random forest method, the kappa coefficient increased by 5.5% and 6.2%, respectively, compared to the kappa coefficient for the baseline Landsat spectral band data input. The highest accuracy was obtained from the addition of both phenology–topography–Landsat spectral bands to the random forest method, achieving a kappa coefficient of 97%. We therefore mapped rubber plantations in Xishuangbanna using the random forest method, with the addition of phenology and topography information from 1990–2020. Our results demonstrated the usefulness of integrating phenology and topography for mapping rubber plantations. The machine learning approach showed great potential for accurate regional mapping, particularly by incorporating plant habitat and ecological information. We found that during 1990–2020, the total area of rubber plantations had expanded to over three times their former area, while natural forests had lost 17.2% of their former area.