scholarly journals A Comparison of Regression Tree Approaches to Modelling the Efficacy of Water Hyacinth Biocontrol Using Multitemporal Spectral Datasets

2018 ◽  
Vol 2018 ◽  
pp. 1-11
Author(s):  
Na’eem Hoosen Agjee ◽  
Onisimo Mutanga ◽  
Michael Gebreselasie ◽  
Riyad Ismail
Keyword(s):  
Water Hyacinth ◽  
Regression Tree ◽  
Regression Trees ◽  
Predictive Performance ◽  
Canopy Reflectance ◽  
Model Interpretation ◽  
Leaf Chlorophyll ◽  
Single Target ◽  
Reflectance Data ◽  
Better Than

Water hyacinth (Eichhornia crassipes) is an exotic plant species that is effectively controlled byNeochetinaspp. weevils. This study is aimed at determining if spectroscopic data may be utilized to predict insect-induced stress on water hyacinth plants. Single target regression trees (STRTs), multitarget regression trees (MTRTs), and random forest multitarget regression trees (RF-MTRTs) have been used to predict feeding scar damage (FSD) and relative leaf chlorophyll content (RLCC) from hyperspectral canopy reflectance data. Results from this study show that the correlation coefficient of STRTs (training accuracy: 76%–97%; validation accuracy: 47%–86%) performs better than MTRTs (training accuracy: 74%–90%; validation accuracy: 45%–77%) for all infestation levels but are difficult to interpret simultaneously. In contrast, MTRTs (size: 23–35 nodes) are much smaller and more interpretable than STRTs (size: 11–47 nodes) because they predict FSD and RLCC simultaneously. Importantly, RF-MTRTs (training accuracy: 95%–98%; validation accuracy: 55%–88%) yield better predictive performance than STRTs and MTRTs for all infestation levels. It is concluded that MTRTs can be utilized for model interpretation as they are more interpretable; however, RF-MTRTs offer an improved predictive performance.

scholarly journals Comparison of Empirical and Physical Modelling for Estimation of Biochemical and Biophysical Vegetation Properties: Field Scale Analysis across an Arctic Bioclimatic Gradient

2020 ◽  
Vol 12 (18) ◽  
pp. 3073
Author(s):  
Blair E. Kennedy ◽  
Douglas J. King ◽  
Jason Duffe
Keyword(s):  
Numerical Optimization ◽  
Vegetation Indices ◽  
Physical Modelling ◽  
Predictive Performance ◽  
High Arctic ◽  
Canopy Reflectance ◽  
Area Index ◽  
Empirical Modelling ◽  
Plant Area Index ◽  
Reflectance Data

To evaluate the potential of multi-angle hyperspectral sensors for monitoring vegetation variables in Arctic environments, empirical and physical modelling using field data was implemented for the retrieval of leaf and canopy chlorophyll content (LCC, CCC) and plant area index (PAI) measured at four sites situated across a bioclimatic gradient in the Western Canadian Arctic. Field reflectance data were acquired with an ASD FieldSpec (305–1075 nm) and used to simulate CHRIS Mode1 spectra (411–997 nm). Multi-angle measurements were taken corresponding to CHRIS view zenith angles (VZA) (−55°, −36°, 0°, +36°, +55°). Empirical modelling compared parametric regression based on vegetation indices (VIs) to non-parametric Gaussian Processes Regression (GPR). In physical modelling, PROSAIL was inverted using numerical optimization and look-up table (LUT) approaches. Cross-validation of the empirical models ranked GPR as best, followed by simple ratio (SR) with optimally selected NIR and red wavelengths, and then ROSAVI using its published wavelengths (mean r2cv = 0.62, 0.58, and 0.54, respectively across all sites, variables, and VZAs). However, the best predictive performance was achieved by SR followed by GPR and ROSAVI (NRMSEcv = 0.12, 0.16, 0.16, respectively). PROSAIL simulated the multi-angle top-of-canopy reflectance well with numerical optimization (r2 = ~0.99, RMSE = 0.004 ± 0.002), but best performing LUT models of LCC, CCC and PAI were poorer than the empirical approaches (mean r2 = 0.48, mean NRMSE = 0.22). PROSAIL performed best at the high Arctic sparsely vegetated site (r2 = 0.57–0.86 for all parameters). Overall, the best performing VZA was −55° for empirical modelling and 0° and ±55° for physical modelling; however, these were not significantly better than the other VZAs. Overall, this study demonstrates that, for Arctic vegetation, nadir narrowband reflectance data used to derive simple empirical VIs with optimally selected bands is a more efficient approach for modelling chlorophyll and PAI than more complex empirical and physical approaches.

scholarly journals Efficacy and safety of neoadjuvant therapy for HER2-positive early breast cancer: a network meta-analysis

2021 ◽  
Vol 13 ◽  
pp. 175883592110069
Author(s):  
Jie Zhang ◽  
Yushuai Yu ◽  
Yuxiang Lin ◽  
Shaohong Kang ◽  
Xinyin Lv ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Neoadjuvant Therapy ◽  
Combination Chemotherapy ◽  
Target Therapy ◽  
Meta Analysis ◽  
Her2 Positive ◽  
Single Target ◽  
Dual Target ◽  
Better Than ◽  
Positive Breast Cancer

Aims: Currently, there are many approaches available for neoadjuvant therapy for human epidermal growth factor receptor 2 (HER2)-positive breast cancer that improve therapeutic efficacy but are also controversial. We conducted a two-step Bayesian network meta-analysis (NMA) to compare odds ratios (ORs) for pathologic complete response (PCR) and safety endpoints. Methods: The Cochrane Central Register of Controlled Trials, PubMed, Embase, and online abstracts from the American Society of Clinical Oncology and San Antonio Breast Cancer Symposium were searched comprehensively and systematically. Phase II/III randomised clinical trials for targeted therapy in at least one arm were included. Results: A total of 9779 published manuscripts were identified, and 36 studies including 10,379 patients were finally included in our analysis. The NMA of PCR showed that dual-target therapy is better than single-target therapy and combination chemotherapy is better than monochemotherapy. However, anthracycline did not bring extra benefits, whether combined with dual-target therapy or single-target therapy. On the other hand, the addition of endocrine therapy in the HER2-positive, hormone receptor (HR)-positive subgroup might have additional beneficial effects but without significant statistical difference. By performing a conjoint analysis of the PCR rate and safety endpoints, we found that ‘trastuzumab plus pertuzumab’ and ‘T-DM1 containing regimens’ were well balanced in terms of efficacy and toxicity in all target regimens. Conclusion: In summary, trastuzumab plus pertuzumab-based dual-target therapy with combination chemotherapy regimens showed the highest efficacy of all optional regimens. They also achieved the best balance between efficacy and toxicity. As our study showed that anthracycline could be replaced by carboplatin, we strongly recommended TCbHP as the preferred choice for neoadjuvant treatment of HER2-positive breast cancer. We also look forward to the potential value of T-DM1 in improving outcomes, which needs further study in future trials.

scholarly journals The Difficulty of Predicting Eastern Spruce Dwarf Mistletoe in Lowland Black Spruce: Model Benchmarking in Northern Minnesota, USA

Forests ◽  
2021 ◽  
Vol 12 (7) ◽  
pp. 843
Author(s):  
Ella R. Gray ◽  
Matthew B. Russell ◽  
Marcella A. Windmuller-Campione
Keyword(s):  
Stand Structure ◽  
Black Spruce ◽  
Forest Health ◽  
Basal Area ◽  
Predictive Performance ◽  
Stand Age ◽  
Management Decisions ◽  
Dwarf Mistletoe ◽  
Growing Seasons ◽  
Model Interpretation

Insects, fungi, and diseases play an important role in forest stand development and subsequently, forest management decisions and treatments. As these disturbance agents commonly occur within and across landscapes, modeling has often been used to inform forest planning and management decisions. However, models are rarely benchmarked, leaving questions about their utility. Here, we assessed the predictive performance of a Bayesian hierarchical model through on–the-ground sampling to explore what features of stand structure or composition may be important factors related to eastern spruce dwarf mistletoe (Arceuthobium pusillum Peck) presence in lowland black spruce (Picea mariana (Mill.) B. S. P.). Twenty-five state-owned stands included in the predictive model were sampled during the 2019 and 2020 growing seasons. Within each stand, data related to the presence of eastern spruce dwarf mistletoe, stand structure, and species composition were collected. The model accurately predicted eastern spruce dwarf mistletoe occurrence for 13 of the 25 stands. The amount of living and dead black spruce basal area differed significantly based on model prediction and observed infestation, but trees per hectare, total living basal area, diameter at breast height, stand age, and species richness were not significantly different. Our results highlight the benefits of model benchmarking to improve model interpretation as well as to inform our understanding of forest health problems across diverse stand conditions.

scholarly journals Toward organism identification through analysis of bacterial colonies.

1977 ◽  
Vol 25 (7) ◽  
pp. 702-706
Author(s):  
M D Graham
Keyword(s):  
Experimental System ◽  
Clinical Problem ◽  
Growth Conditions ◽  
Surface Scattering ◽  
Bacterial Identification ◽  
Multi Wavelength ◽  
Boundary Characteristics ◽  
Organism Identification ◽  
Reflectance Data ◽  
Better Than

The clinical problem of bacterial identification has been approached by applying pattern-recognition techniques to multi-wavelength surface-scattering and reflectance data derived from real-time scans of isolated colonies. Preliminary results, obtained from blood-agar plates inoculated with a mixture of staphylococci, streptococci and escherichieae, indicate that these organisms can be differentiated with better than 90% certainty, provided the colonies are physically separated and their growth conditions closely controlled. Data collection and classification characteristics of the experimental system are briefly described; it is felt that the technique, possibly expanded to include boundary characteristics of the colonies, may offer a viable means of identifying clinically important bacteria.

scholarly journals PlotMI: visualization of pairwise interactions and positional preferences learned by a deep learning model from sequence data

2021 ◽  
Author(s):  
Tuomo Hartonen ◽  
Teemu Kivioja ◽  
Jussi Taipale
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Sequence Data ◽  
Predictive Performance ◽  
Learning Model ◽  
Biological Research ◽  
Learning Approaches ◽  
Learning Models ◽  
Model Interpretation ◽  
Pairwise Interactions

Deep learning models have in recent years gained success in various tasks related to understanding information coded in the DNA sequence. Rapidly developing genome-wide measurement technologies provide large quantities of data ideally suited for modeling using deep learning or other powerful machine learning approaches. Although offering state-of-the art predictive performance, the predictions made by deep learning models can be difficult to understand. In virtually all biological research, the understanding of how a predictive model works is as important as the raw predictive performance. Thus interpretation of deep learning models is an emerging hot topic especially in context of biological research. Here we describe plotMI, a mutual information based model interpretation strategy that can intuitively visualize positional preferences and pairwise interactions learned by any machine learning model trained on sequence data with a defined alphabet as input. PlotMI is freely available at https://github.com/hartonen/plotMI.

scholarly journals A Comparison between the MODIS Product (MOD17A2) and a Tide-Robust Empirical GPP Model Evaluated in a Georgia Wetland

2018 ◽  
Vol 10 (11) ◽  
pp. 1831 ◽  
Author(s):  
Jianbin Tao ◽  
Deepak Mishra ◽  
David Cotten ◽  
Jessica O’Connell ◽  
Monique Leclerc ◽  
...  
Keyword(s):  
Eddy Covariance ◽  
Vegetation Index ◽  
Gross Primary Production ◽  
Training Data ◽  
Environmental Drivers ◽  
Canopy Reflectance ◽  
Co2 Fluxes ◽  
Moisture Index ◽  
Validation Data ◽  
Reflectance Data

Despite the importance of tidal ecosystems in the global carbon budget, the relationships between environmental drivers and carbon dynamics in these wetlands remain poorly understood. This limited understanding results from the challenges associated with in situ flux studies and their correlation with satellite imagery which can be affected by periodic tidal flooding. Carbon dioxide eddy covariance (EC) towers are installed in only a few wetlands worldwide, and the longest eddy-covariance record from Georgia (GA) wetlands contains only two continuous years of observations. The goals of the present study were to evaluate the performance of existing MODIS Gross Primary Production (GPP) products (MOD17A2) against EC derived GPP and develop a tide-robust Normalized Difference Moisture Index (NDMI) based model to predict GPP within a Spartina alterniflora salt marsh on Sapelo Island, GA. These EC tower-based observations represent a basis to associate CO2 fluxes with canopy reflectance and thus provide the means to use satellite-based reflectance data for broader scale investigations. We demonstrate that Light Use Efficiency (LUE)-based MOD17A2 does not accurately reflect tidal wetland GPP compared to a simple empirical vegetation index-based model where tidal influence was accounted for. The NDMI-based GPP model was capable of predicting changes in wetland CO2 fluxes and explained 46% of the variation in flux-estimated GPP within the training data, and a root mean square error of 6.96 g C m−2 in the validation data. Our investigation is the first to create a MODIS-based wetland GPP estimation procedure that demonstrates the importance of filtering tidal observations from satellite surface reflectance data.

Sign in / Sign up

Export Citation Format

Share Document