Jin Liu

Bio: Jin Liu is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Lidar & Forest ecology. The author has an hindex of 12, co-authored 21 publications receiving 583 citations. Previous affiliations of Jin Liu include Peking University.

Effects of nitrogen-fixing and non-nitrogen-fixing tree species on soil properties and nitrogen transformation during forest restoration in southern China

Abstract: The role of different plantation tree species in soil nutrient cycling is of great importance for the restoration of degraded lands. The objective of the present study was to evaluate the potential of N-fixing and non-N-fixing tree species to recuperate degraded land in southern China. The soil properties and N transformations in six forest types (two N-fixing plantations, three non-N-fixing plantations and a secondary shrubland) established in 1984 were compared. The N-fixing forests had 40–50% higher soil organic matter and 20–50% higher total nitrogen concentration in the 0–5 cm soils than the non-N-fixing forests. Soil inorganic N was highest under the secondary shrubland. The N-fixing Acacia auriculiformis plantation had the highest soil available P. There were no significant differences in soil N mineralization and nitrification among the forest types, but seasonal variation in these N processes was highly significant. In the rainy season, the rates of N mineralization (7.41–11.3 kg N ha−1 ...

Mapping Global Forest Aboveground Biomass with Spaceborne LiDAR, Optical Imagery, and Forest Inventory Data

Abstract: As a large carbon pool, global forest ecosystems are a critical component of the global carbon cycle. Accurate estimations of global forest aboveground biomass (AGB) can improve the understanding of global carbon dynamics and help to quantify anthropogenic carbon emissions. Light detection and ranging (LiDAR) techniques have been proven that can accurately capture both horizontal and vertical forest structures and increase the accuracy of forest AGB estimation. In this study, we mapped the global forest AGB density at a 1-km resolution through the integration of ground inventory data, optical imagery, Geoscience Laser Altimeter System/Ice, Cloud, and Land Elevation Satellite data, climate surfaces, and topographic data. Over 4000 ground inventory records were collected from published literatures to train the forest AGB estimation model and validate the resulting global forest AGB product. Our wall-to-wall global forest AGB map showed that the global forest AGB density was 210.09 Mg/ha on average, with a standard deviation of 109.31 Mg/ha. At the continental level, Africa (333.34 ± 63.80 Mg/ha) and South America (301.68 ± 67.43 Mg/ha) had higher AGB density. The AGB density in Asia, North America and Europe were 172.28 ± 94.75, 166.48 ± 84.97, and 132.97 ± 50.70 Mg/ha, respectively. The wall-to-wall forest AGB map was evaluated at plot level using independent plot measurements. The adjusted coefficient of determination (R2) and root-mean-square error (RMSE) between our predicted results and the validation plots were 0.56 and 87.53 Mg/ha, respectively. At the ecological zone level, the R2 and RMSE between our map and Intergovernmental Panel on Climate Change suggested values were 0.56 and 101.21 Mg/ha, respectively. Moreover, a comprehensive comparison was also conducted between our forest AGB map and other published regional AGB products. Overall, our forest AGB map showed good agreements with these regional AGB products, but some of the regional AGB products tended to underestimate forest AGB density.

An integrated UAV-borne lidar system for 3D habitat mapping in three forest ecosystems across China

Abstract: In recent decades, global biodiversity has gradually diminished due to the increasing pressure from anthropogenic activities and climatic change. Accurate estimations of spatially continuous three-dimensional 3D vegetation structures and terrain information are prerequisites for biodiversity studies, which are usually unavailable in current ecosystem-wide studies. Although the airborne lidar technique has been successfully used for mapping 3D vegetation structures at landscape and regional scales, the relatively high cost of airborne lidar flight mission has significantly limited its applications. The unmanned aerial vehicle UAV provides an alternative platform for lidar data acquisition, which can largely lower the cost and provide denser lidar points compared with airborne lidar. In this study, we implemented a low-cost UAV-borne lidar system, including both a hardware system and a software system, to collect and process lidar data for biodiversity studies. The implemented UAV-borne lidar system was tested in three different ecosystems across China, including a needleleaf–broadleaf mixed forest, an evergreen broadleaf forest, and a mangrove forest. Various 3D vegetation structure parameters e.g. canopy height model, canopy cover, leaf area index, aboveground biomass were derived from the UAV-borne lidar data. The results show that the implemented UAV-borne lidar system can generate very high resolution 3D terrain and vegetation information. The developed UAV-based hardware and software systems provide a turn-key solution for the use of UAV-borne lidar data on biodiversity studies.

Deep Learning: Individual Maize Segmentation From Terrestrial Lidar Data Using Faster R-CNN and Regional Growth Algorithms.

Abstract: The rapid development of light detection and ranging (Lidar) provides a promising way to obtain three-dimensional (3D) phenotype traits with its high ability of recording accurate 3D laser points. Recently, Lidar has been widely used to obtain phenotype data in the greenhouse and field with along other sensors. Individual maize segmentation is the prerequisite for high throughput phenotype data extraction at individual crop or leaf level, which is still a huge challenge. Deep learning, a state-of-the-art machine learning method, has shown high performance in object detection, classification, and segmentation. In this study, we proposed a method to combine deep leaning and regional growth algorithms to segment individual maize from terrestrial Lidar data. The scanned 3D points of the training site were sliced row and row with a fixed 3D window. Points within the window were compressed into deep images, which were used to train the Faster R-CNN (region-based convolutional neural network) model to learn the ability of detecting maize stem. Three sites of different planting densities were used to test the method. Each site was also sliced into many 3D windows, and the testing deep images were generated. The detected stem in the testing images can be mapped into 3D points, which were used as seed points for the regional growth algorithm to grow individual maize from bottom to up. The results showed that the method combing deep leaning and regional growth algorithms was promising in individual maize segmentation, and the values of r, p, and F of the three testing sites with different planting density were all over 0.9. Moreover, the height of the truly segmented maize was highly correlated to the manually measured height (R2> 0.9). This work shows the possibility of using deep leaning to solve the individual maize segmentation problem from Lidar data.

Stem–Leaf Segmentation and Phenotypic Trait Extraction of Individual Maize Using Terrestrial LiDAR Data

Abstract: Accurate and high throughput extraction of crop phenotypic traits, as a crucial step of molecular breeding, is of great importance for yield increasing. However, automatic stem–leaf segmentation as a prerequisite of many precise phenotypic trait extractions is still a big challenge. Current works focus on the study of the 2-D image-based segmentation, which are sensitive to illumination and occlusion. Light detection and ranging (LiDAR) can obtain accurate 3-D information with its active laser scanning and strong penetration ability, which breaks through phenotyping from 2-D to 3-D. However, few researches have addressed the problem of the LiDAR-based stem–leaf segmentation. In this paper, we proposed a median normalized-vector growth (MNVG) algorithm, which can segment stem and leaf with four steps, i.e., preprocessing, stem growth, leaf growth, and postprocessing. The MNVG method was tested by 30 maize samples with different heights, compactness, leaf numbers, and densities from three growing stages. Moreover, phenotypic traits at leaf, stem, and individual levels were extracted with the truly segmented instances. The mean accuracy of segmentation at point level in terms of the recall, precision, F-score, and overall accuracy were 0.92, 0.93, 0.92, and 0.93, respectively. The accuracy of phenotypic trait extraction in leaf, stem, and individual levels ranged from 0.81 to 0.95, 0.64 to 0.97, and 0.96 to 1, respectively. To our knowledge, this paper proposed the first LiDAR-based stem–leaf segmentation and phenotypic trait extraction method in agriculture field, which may contribute to the study of LiDAR-based plant phonemics and precise agriculture.

Applied Linear Regression Models

Abstract: (1991). Applied Linear Regression Models. Journal of Quality Technology: Vol. 23, No. 1, pp. 76-77.

Global patterns of land-atmosphere fluxes of carbon dioxide, latent heat, and sensible heat derived from eddy covariance, satellite, and meteorological observations

Abstract: We upscaled FLUXNET observations of carbon dioxide, water, and energy fluxes to the global scale using the machine learning technique, model tree ensembles (MTE). We trained MTE to predict site-level gross primary productivity (GPP), terrestrial ecosystem respiration (TER), net ecosystem exchange (NEE), latent energy (LE), and sensible heat (H) based on remote sensing indices, climate and meteorological data, and information on land use. We applied the trained MTEs to generate global flux fields at a 0.5 degrees x 0.5 degrees spatial resolution and a monthly temporal resolution from 1982 to 2008. Cross-validation analyses revealed good performance of MTE in predicting among-site flux variability with modeling efficiencies (MEf) between 0.64 and 0.84, except for NEE (MEf = 0.32). Performance was also good for predicting seasonal patterns (MEf between 0.84 and 0.89, except for NEE (0.64)). By comparison, predictions of monthly anomalies were not as strong (MEf between 0.29 and 0.52). Improved accounting of disturbance and lagged environmental effects, along with improved characterization of errors in the training data set, would contribute most to further reducing uncertainties. Our global estimates of LE (158 +/- 7 J x 10(18) yr(-1)), H (164 +/- 15 J x 10(18) yr(-1)), and GPP (119 +/- 6 Pg C yr(-1)) were similar to independent estimates. Our global TER estimate (96 +/- 6 Pg C yr(-1)) was likely underestimated by 5-10%. Hot spot regions of interannual variability in carbon fluxes occurred in semiarid to semihumid regions and were controlled by moisture supply. Overall, GPP was more important to interannual variability in NEE than TER. Our empirically derived fluxes may be used for calibration and evaluation of land surface process models and for exploratory and diagnostic assessments of the biosphere.

Review on Convolutional Neural Networks (CNN) in vegetation remote sensing

Abstract: Identifying and characterizing vascular plants in time and space is required in various disciplines, e.g. in forestry, conservation and agriculture. Remote sensing emerged as a key technology revealing both spatial and temporal vegetation patterns. Harnessing the ever growing streams of remote sensing data for the increasing demands on vegetation assessments and monitoring requires efficient, accurate and flexible methods for data analysis. In this respect, the use of deep learning methods is trend-setting, enabling high predictive accuracy, while learning the relevant data features independently in an end-to-end fashion. Very recently, a series of studies have demonstrated that the deep learning method of Convolutional Neural Networks (CNN) is very effective to represent spatial patterns enabling to extract a wide array of vegetation properties from remote sensing imagery. This review introduces the principles of CNN and distils why they are particularly suitable for vegetation remote sensing. The main part synthesizes current trends and developments, including considerations about spectral resolution, spatial grain, different sensors types, modes of reference data generation, sources of existing reference data, as well as CNN approaches and architectures. The literature review showed that CNN can be applied to various problems, including the detection of individual plants or the pixel-wise segmentation of vegetation classes, while numerous studies have evinced that CNN outperform shallow machine learning methods. Several studies suggest that the ability of CNN to exploit spatial patterns particularly facilitates the value of very high spatial resolution data. The modularity in the common deep learning frameworks allows a high flexibility for the adaptation of architectures, whereby especially multi-modal or multi-temporal applications can benefit. An increasing availability of techniques for visualizing features learned by CNNs will not only contribute to interpret but to learn from such models and improve our understanding of remotely sensed signals of vegetation. Although CNN has not been around for long, it seems obvious that they will usher in a new era of vegetation remote sensing.

A generalized, bioclimatic index to predict foliar phenology in response to climate

Abstract: The phenological state of vegetation significantly affects exchanges of heat, mass, and momentum between the Earth's surface and the atmosphere. Although current patterns can be estimated from satellites, we lack the ability to predict future trends in response to climate change. We searched the literature for a common set of variables that might be combined into an index to quantify the greenness of vegetation throughout the year. We selected as variables: daylength (photoperiod), evaporative demand (vapor pressure deficit), and suboptimal (minimum) temperatures. For each variable we set threshold limits, within which the relative phenological performance of the vegetation was assumed to vary from inactive (0) to unconstrained (1). A combined Growing Season Index (GSI) was derived as the product of the three indices. Ten-day mean GSI values for nine widely dispersed ecosystems showed good agreement (r>0.8) with the satellite-derived Normalized Difference Vegetation Index (NDVI). We also tested the model at a temperate deciduous forest by comparing model estimates with average field observations of leaf flush and leaf coloration. The mean absolute error of predictions at this site was 3 days for average leaf flush dates and 2 days for leaf coloration dates. Finally, we used this model to produce a global map that distinguishes major differences in regional phenological controls. The model appears sufficiently robust to reconstruct historical variation as well as to forecast future phenological responses to changing climatic conditions.