The growing applications of near infrared (NIR) spectroscopy in wood quality control and monitoring necessitates focusing on data-driven methods to develop predictive models. Despite the advancements in analyzing NIR spectral data, literature on wood science and engineering has mainly utilized the classic model development methods, such as principal component analysis (PCA) regression or partial least squares (PLS) regression, with relatively limited studies conducted on evaluating machine learning (ML) models, and specifically, artificial neural networks (ANNs). This could potentially limit the performance of predictive models, specifically for some wood properties, such as tracheid width that are both time-consuming to measure and challenging to predict using spectral data. This study aims to enhance the prediction accuracy for tracheid width using deep neural networks and tree-based ensemble learning algorithms on a dataset consisting of 2018 samples and 692 features (NIR spectra wavelengths). Accordingly, NIR spectra were fed into multilayer perceptron (MLP), 1 dimensional-convolutional neural networks (1D-CNNs), random forest, TreeNet gradient-boosting, extreme gradient-boosting (XGBoost), and light gradient-boosting machine (LGBM). It was of interest to study the performance of the models with and without applying PCA to assess how effective they would perform when analyzing NIR spectra without employing dimensionality reduction on data. It was shown that gradient-boosting machines outperformed the ANNs regardless of the number of features (data dimension). All the models performed better without PCA. It is concluded that tree-based gradient-boosting machines could be effectively used for wood characterization utilizing a medium-sized NIR spectral dataset.

Efforts to restore longleaf pine across the southeast United States have occurred on two distinct site types, cutover forests and old agricultural fields. We measured wood and bark physical properties of unthinned planted longleaf pine from sixteen stands across Georgia, ages 12 to 25, with eight stands sampled from each site type. Three-hundred and twenty trees were felled and 3,572 disks collected from within the trees. Wood and bark specific gravity (SG), moisture content (MC), and proportion of bark were measured. Non-linear mixed effects models were developed to predict the variation in wood and bark SG with respect to relative height, age, and site type. Cutover sites had higher whole-tree wood SG (0.504 vs 0.455) and bark SG (0.374 vs 0.347) than old agricultural fields. The models explained 50% and 37% of the variability in wood and bark SG, respectively. Moisture content models were fitted as a function of SG for wood (R2 = 0.87) and bark (R2 = 0.71). Bark thickness, dry mass, and green volume were higher for cutover forest sites. Trees sampled included both non-defect and defect-containing trees, however, no significant differences in the wood physical properties were found. These results provide important information for the utilization of plantation longleaf pine.

Water resources and environment management is important for all living beings on the earth's surface. Capacity of the water resources are reducing due to soil erosion or sedimentation and quality also decreasing due to overflow of the reservoir. The analysis of sedimentation data of Indian reservoirs show that the annual siltation rate has been generally 1.5 to 3 times more than the designed rate and the reservoirs are generally losing capacity at the rate of 0.30 to 0.92 per cent annually (NRSA). Remote sensing is a useful tool for in-situ monitoring of suspended sediments in surface water for a variety of reasons such as the multi spectral nature, large area coverage, and temporal data sets. Considering the necessity of the assessment of the sediment as well as advantage of the remote sensing technique. The present study is taken to develop the spectral signature library for different sediment concentration. These results integrating with satellite data yield significant. A controlled experiment was conducted in outdoors condition with a 40 lt water tank (white painted) having natural sunlight condition. A different soil series viz., Gulvanch, Targaon, Rahuri, Pather etc. were added and suspended in the tank filled with water. A total 10 levels of Suspended Sediment Concentration (SSC) (from 1000 ppm to 10000 ppm) were added for each type of treatment. Reflectance was recorded using an HR 1024 Spectroradiometer, and reflectance factor was computed and analyzed. The linearity in the SSC-reflectance relationship increased with wavelength between 400 and 900 nm. For relationship between suspended sediment concentration and reflectance data four different functions, viz., exponential, linear, logarithmic and power were tried. The best fit model was found to be power by regression analysis.

One of the major applications of remote sensing in environmental resources management and decision making is the detection and quantitative assessment of soil and vegetation. Operational monitoring of vegetative cover by remote sensing currently involves the utilisation of vegetation indices (VI), it is the function of the reflectance in red (R) and near-infrared (NIR) spectral bands. Although many variations exist, most of them are the ratio of the reflection of light in the red and NIR sections of the spectrum to separate the landscape into water, soil, and vegetation. The present research was conducted for development of soil line and vegetation indices ratio vegetative index (RVI) and soil adjusted vegetative index (SAVI) and to develop relationship between vegetation indices and bulk density. Four soil series namely Gulvanch, Targaon, Rahuri and Pather series were used in the study. The soil line, a linear relationship between bare soil reflectance observed in two IR and NIR waveband which is widely used for interpretation of remotely sensed data. Soil line based vegetation indices are introduced which may be used for assessment of water use, plant stress, crop production and requires knowledge of external environment. Slope, intercept of soil line were developed for four different series and used for estimation of vegetative indices. The maximum slope for soil line was for Targaon series followed by Rahuri, Pather and Gulvanch series. Relationships between bulk density and vegetation indices (RVI, SAVI) were developed by curve fitting method, linear function was most suitable function. Relationship between vegetation indices (SAVI and RVI) and bulk density was developed which can be used for determination of physical properties from remotely sensed data.

Community forestry practices have proven to be successful in forest resource conservation and utilization in Nepal. Nevertheless, inclusive decision-making processes and equitable benefit-sharing among each household pose significant challenges to the Community Forestry Users Groups (CFUGs). The four key elements of good governance: Participation, Transparency, Accountability, and Predictability, each with their four own local indicators, were employed to measure the governance status in two CFUGs: Bosan and Hattiban Mahila in Kathmandu district. We collected data through a questionnaire survey (n=95), focus group discussions, and key informant surveys. The results showed that the general status of governance in Bosan CFUG was 'Good' (43 out of a total attainable score of 64), whereas that of Hattiban Mahila CFUG was 'Medium'(32 out of a total attainable score of 64). Scores for Transparency, Accountability, and Predictability in Bosan CFUG managed by men and women alike were found to be higher than those of Hattiban Mahila CFUG, which was managed mostly by women. Both the CFUGs received the same score for good governance element: Participation. This study helps policymakers to formulate effective programs for CFUGs members to improve the governance system in such forestry user groups.