Variations In Moisture Content Research Articles

Computational modeling of spatial variation in moisture content and temperature distribution in corn at different superheated steam temperatures

The Superheated steam has been shown to be more effective than hot air for drying corn. Modeling studies have been carried out in fluidized bed dryers to determine the moisture and heat transfer characteristics of corn, but there are no modeling studies for a single corn kernel. Knowledge of heat and mass transfer characteristics in a single kernel would produce a better understanding of steam characteristics needed for specific drying rates. The study sought to determine the influence of steam temperature and velocity on the drying rate of a corn kernel. It used computational fluid dynamics (CFD) to model the transfer of heat and moisture between the corn kernel and superheated steam. The simulation used cone geometry to represent the corn kernel. The kernel had characteristic dimensions and 20% initial moisture content. The condition of the steam, which was typical of that found in industry, had temperatures of 120–200°C and velocities of 0.5–1.5 m/s. There was a decrease in the duration of the initial condensation phase as the temperature of superheated steam increased from 120°C to 200°C. The highest steam temperature and velocity resulted in the shortest duration for steam condensation. Contrary to what has been reported, there was no moisture loss from the corn kernel when exposed to superheated steam at 120°C, which may be due to how heat was retained in the drying chamber. Thus, the processes of tapping steam and retaining heat are important elements in the operation of industrial steam driers.

Development and Performance Evaluation of Maize Stalk Harvester

A power operated maize stalk harvester was designed and developed in the Dept. of Farm Machinery and Power Engineering, MPUAT, Udaipur, Rajasthan during 2018-19. The objective of this study is to optimize the operational parameters of the maize stalk harvesting by using the RSM techniques. The effects of independent parameters i.e., blade speed (2000, 4000 and 6000 rpm) and stalk moisture content (38, 42 and 46%) on cutting efficiency (%) and fuel consumption (l/h) were studied. To correlate the independent parameters with the dependent parameters, the central composite rotatable design (CCRD) method with a quadratic model was used. The findings indicated that the variations in blade speed and stalk moisture content affected the cutting efficiency (%) and fuel consumption (l/h). To assess the statistical significance of the model, an analysis of variance (ANOVA) was performed, which showed good agreement between the experimental data and data predicted by the model. The blade speed of 4000 rpm and stalk moisture content of 46.0% was found to be the optimum for power operated maize stalk harvester with the 96.52% cutting efficiency and 0.72 l/h fuel consumption.

The Influence of Water Concentration on High-Temperature Reactive Evaporation and Condensation of Cr in 800°C Air

Reactive evaporation of Cr from stainless steels used in solid oxide electrochemical systems, such as solid oxide fuel cell (SOFC) and solid oxide electrolysis cell (SOEC) systems, is well-documented as the cause of Cr poisoning; however, the condensation and interactions of volatilized Cr species onto and with surrounding interfaces during complex and dynamic system exposures is less understood. Understanding these interactions during operation is critical for improving system performance and safeguarding environmental, health and safety, as some condensed Cr forms toxic hexavalent chromium (Cr(VI)) species. The objective of this study is to investigate and report on condensation pathways of Cr vapors within representative high-temperature system environments. To accomplish this objective, Cr vapors, produced by high-temperature (800°C) air exposures of trivalent chromium (Cr(III)) oxide (Cr2O3) powder with variable moisture content, were condensed onto various ceramic materials at lower temperatures (<400°C). Both the total amount of Cr and ratios of oxidation states were measured using ICP-MS and colorimetric analyses. An increase of Cr condensation was observed with increased water content, with similar Cr(VI) to Cr(III) ratios. Results and interpretations are discussed in context of improved understanding of Cr reactive evaporation and condensation in SOFC/SOEC and related high-temperature materials and systems.

Research on Landslide Hydrology and Hydrogeological Disaster Monitoring

The triggering of landslides is strongly related to hydrological processes, as variations in soil moisture content and pore water pressure affect variations in soil mechanical properties [...]

Hydromechanical behavior of unsaturated swelling clays: review

Expansive soils are materials composed mainly of active minerals of the smectite family, where montmorillonite is an essential member of that group. These types of soils tend to undergo volumetric changes due to variations in moisture content. Many geotechnical engineering practices, such as dam core design or subgrade compaction, require a thorough evaluation of the response of these soils to determine placement conditions. However, the main problem in evaluating the mechanical response of this type of soil lies in the nonlinear nature, which limits the use of most classical constitutive models that apply the basic rules of elastoplasticity. In this study, an analysis is carried out to understand the hydromechanical behavior of expansive soils in saturated and unsaturated conditions. Direct and indirect physical evidence is presented and discussed to evaluate the hydraulic response of the soil structural elements responsible for these adverse dynamics from a global (expansive phenomena as a whole) and individual (swelling and shrinkage) perspective. Since the response of these soils is hydrostatic dependent, the locus of water movement in porous media is examined, starting from the Richards equation (1931), in order to consider the flow mechanisms in unsaturated media under transient conditions.

Gaussian Process Regression for Quantitative Degree of Polymerization Analysis of Oil-Paper Insulation by EPO-NIRS: A Solution to Field Moisture

In recent years, the near infrared (NIR) spectroscopy has been used in prediction of the degree of polymerization (DP) of oil-paper insulation, but the practices show that the field moisture has a significant influence on the acquired spectra. In this paper, an EPO-GPR model is proposed to eliminate the interference of external moisture and hence to improve the prediction performance of DP of insulating paper in the laboratory as well as on-site experiments. In this model, external parameter orthogonalization (EPO) extracts the differences between the insulating paper samples with varying moisture contents and builds a projection matrix orthogonal to the moisture spectral information; the Gaussian process regression (GPR) with optimized Matérn kernel is employed to mapping the correlation between the spectra and DP of insulating paper. Compared with classical PLS and BPNN models, the EPO-GPR model achieves high prediction accuracy in the laboratory testing (RMSE of 71) and field experiments (RMSE of ∼ 60). The proposed EPO-GPR model can provide a solution to field moisture when using the NIR spectroscopy technique to on-site assess the aging condition of insulating papers.

The effect of saturation and salts on the rigidity of fine-grained material

Repeated multi-channel analysis of surface waves (MASW) and horizontal to vertical spectral ratio (HVSR) experiments were conducted on a hummock within a large landslide in east-central Utah adjacent to a small wetland. Stakes were placed into the ground to ensure identical array geometries and geophone locations. The landslide is an admixture of fine-grained material (clay, quartz and Na-plagioclase) and intermediate-composition volcanic clasts. A prominent crust of Na-salts covered the hummock surface, produced by evapotranspiration of shallow groundwater associated with the adjacent fen.The experiments produced three primary observations. First, on any given day, the Rayleigh wave frequency spectra were highly reproducible between individual experiments. Second, from May to October the spectra exhibited high variability between experiments conducted weeks apart, especially at frequencies <20 Hz. Third, a persistent subsurface boundary exists across which Vs increases from ~175 to ~300 m/s. However, that boundary migrated over time from a depth of ~5 to ~4 m.The low velocity of the upper ~5 m subsurface layer represents poorly-compacted landslide material, perhaps weakened from high Na+ concentrations. However, the variability in frequency spectra and upward migration of the boundary must have arisen from changing moisture and salt content over time. The fen was instrumented with a piezometer that showed an overall ~1 m decline in water levels from May to October with small, superimposed recharge events resulting from summer monsoon rains.This study leads to two important conclusions. Specific to this site and perhaps others, variable moisture content can affect capillary forces and the proportion of evaporite cements in the shallow subsurface that are manifested in strikingly different frequency spectra and migrating stiffness (Vs) boundaries. More generally, moisture and salt content can affect estimates of subsurface stiffness, including the position of apparent boundaries within unconsolidated materials.

Starch intrinsic crystals affected the changes of starch structures and digestibility during microwave heat-moisture treatment

The structural and functional changes of starch during hydrothermal treatment are influenced by its intrinsic properties. However, how the intrinsic crystalline structures of starch affect changes in structure and digestibility during microwave heat-moisture treatment (MHMT) has not been well understood. In this study, we prepared starch samples with varying moisture content (10 %, 20 %, and 30 %) and A-type crystal content (4.13 %, 6.81 %, and 16.35 %) and investigated the changes in their structures and digestibility during MHMT. Results showed that starch with a high A-type crystal content (16.35 %) and moisture levels of 10 % to 30 % exhibited less ordered structures after MHMT, while starches with lower A-type crystal content (4.13 % to 6.18 %) and moisture content of 10 % to 20 % showed more ordered structures after treatment; but less ordered structures when the moisture content was 30 %. All starch samples had lower digestibility after MHMT and cooking; however, starches with lower A-type crystal content (4.13 % to 6.18 %) and moisture content of 10 % to 20 % displayed significantly lower digestibility after treatment compared to modified starches. Accordingly, starches contained content of A-type crystals of 4.13 %–6.18 % and moisture of 10 %–20 % potentially had better reassembly behaviors during the MHMT to slow starch digestibility in a larger magnitude.

Near-Surface Soil Moisture Characterization in Mississippi’s Highway Slopes Using Machine Learning Methods and UAV-Captured Infrared and Optical Images

Near-surface soil moisture content variation is a major factor in the frequent shallow slope failures observed on Mississippi’s highway slopes built on expansive clay. Soil moisture content variation is monitored generally through borehole sensors in highway embankments and slopes. This point monitoring method lacks spatial resolution, and the sensors are susceptible to premature failure due to wear and tear. In contrast, Unmanned/Uncrewed Aerial Vehicles (UAVs) have higher spatial and temporal resolutions that enable more efficient monitoring of site conditions, including soil moisture variation. The current study focused on developing two methods to predict soil moisture content (θ) using UAV-captured optical and thermal combined with machine learning and statistical modeling. The first method used Red, Green, and Blue (RGB) color values from UAV-captured optical images to predict θ. Support Vector Machine for Regression (SVR), Extreme Gradient Boosting (XGB), and Multiple Linear Regression (MLR) models were trained and evaluated for predicting θ from RGB values. The XGB model and MLR model outperformed the SVR model in predicting soil moisture content from RGB values. The R2 values for the XGB and MLR models were &gt;0.9 for predicting soil moisture when compared to SVR (R2 = 0.25). The Root Mean Square Error (RMSE) for XGB, SVR, and MLR were 0.009, 0.025, and 0.01, respectively, for the test dataset, affirming that XGB was the best-performing model among the three models evaluated, followed by MLR and SVR. The better-performing XGB and MLR models were further validated by predicting soil moisture using unseen input data, and they provided good prediction results. The second method used Diurnal Land Surface Temperature variation (ΔLST) from UAV-captured Thermal Infrared (TIR) images to predict θ. TIR images of vegetation-covered areas and bare ground areas of the highway embankment side slopes were processed to extract ΔLST amplitudes. The underlying relationship between soil surface thermal inertia and moisture content variation was utilized to develop a predictive model. The resulting single-parameter power curve fit model accurately predicted soil moisture from ΔLST, especially in vegetation-covered areas. The power curve fit model was further validated on previously unseen TIR, and it predicted θ with an accuracy of RMSE = 0.0273, indicating good prediction performance. The study was conducted on a field scale and not in a controlled environment, which aids in the generalizability of the developed predictive models.

Using 1H and 23Na NMR relaxometry as a novel tool to monitor the moisture and salt distribution in commercial low-moisture part skim mozzarella

Zonal variations in 1H or 23Na content in commercial low-moisture part-skim mozzarella with a uniform salt distribution, obtained by dry-salting, or with a salt gradient, obtained by dry-salting and brining, were profiled using a combined 1H and 23Na NMR relaxometry procedure. 1D concentration–distance profiles were constructed in all cheeses from the surface to the core. Rapid, non-invasive, (∼21 min) distinction between dry-salted and brined cheese was enabled. Uptake of salt in cheese brined for 0–24 h was determined, and the derived effective diffusion coefficient of 23Na (3.23 × 10−10 m2 s−1) compared favourably with values reported for other semi-hard cheeses during brining; the 23Na concentration–distance profiles of brined cheese stored for 2–44 d at 4 °C corresponded to an effective diffusion coefficient of about 5.21 × 10−10 m2 s−1. Small variations in moisture content in the cheese could not be distinguished from the random fluctuations in 1H signal intensity.

Quantification of design associated engineering properties of sesame (Sesamum indicum L.) seed varieties as a function of moisture content

AbstractThe investigation was intended to examine the influence of selected moisture levels (4.26, 12.66, 25.31, 37.89, 50.21% wet basis) on engineering properties namely, dimensional, gravimetric, frictional, aerodynamic as well as mechanical properties of five selected varieties of sesame seed namely GT‐3, GT‐4, GJT‐5, GT‐6, and TKG 22. The investigation finds out that fluctuations in moisture level significantly (p ≤ 0.05) influenced the engineering properties assessed. Increase in moisture content influenced a rise in length, width, thickness, geometric mean diameter, arithmetic mean diameter, sphericity, volume, volumetric expansion coefficient, elongation ratio, flakiness ratio, surface area, projected area, thousand seeds weight, compressibility index, Hausner ratio, angle of repose, coefficient of friction, terminal velocity and Reynolds number of selected sesame verities. Whereas, a reverse trend was observed in aspect ratio, true density, bulk density, tapped densities, drag coefficient, and hardness with moisture content variation. The frictional characteristic of the seed showed improved stability with less flow ability at higher moisture levels. These outcomes disclosed that variation of seed moisture content is authoritative during designing and construction of machinery and process equipment related to sesame. It may be also beneficial in computation of design for hoppers, silos, conveyors, drying, and heat transfer equipment as well as other sesame seed‐related process and handling equipment.

Influence of Initial Moisture and Reactive MgO Content on Mechanical and Microstructural Characteristics of Carbonated Reactive Magnesia Treated Soft Clay

Soft clay presents many problems in the construction of infrastructures, which can be well solved by using effective solidification materials and technologies. The carbonated reactive magnesia (CRM) comes to the fore for its superiority in energy-saving and high solidification efficiency. Nevertheless, research on the applicability of CRM in soft clay solidifying is limited. In the current study, two major factors, including initial moisture content (w0) and reactive MgO content (Cm), were examined by measuring the unconfined compressive strength (UCS), mass and volume variations, and moisture content variation of CRM-treated soft clay. The intrinsic mechanisms were discussed based on the mercury intrusion porosimetry (MIP), scanning electron microscopy (SEM), and X-ray diffraction (XRD) tests. The findings reveal that carbonated specimens with low Cm (≤ 25%) or w0 (≤ 25%) suffer from severe volumetric expansion and cracks, which cause serious reductions in UCS, and the strength of these specimens can be even much lower than that of the uncarbonated ones. Specimens with high Cm and w0 acquire satisfactory strength by carbonation, and the highest UCS can exceed 4 MPa, indicating that the CRM is capable of solidifying soft clay. Water and MgO are both vital for the crystallization of hydrated magnesium carbonates (HMCs), and Cm is also beneficial for restricting volumetric expansion and reducing macropores; while proper w0 is required for the formation and evolution of HMCs, especially the nesquehonite.

Performance of 3D-printed samples based on starch treated by radio frequency energy

In this study, we investigated changes in the chain length distribution, molecular weight distribution, amylose content, microstructures, thermal properties and rheological properties of potato starch following radio frequency (RF) electromagnetic fields exposure with varying moisture content (30, 40, 50, 60, 70%, w/w). We identified a RF-modified moisture content suitable for 3D printing. Our results showed that RF treatment roughened the starch surface and broke down the longer chains into shorter ones, which reduced the molecular weight, viscosity, and pasting temperature of the starch. The RF-treated starch gels showed better printing performance than untreated potato gels. In addition, changes in the physicochemical properties of the starch became more pronounced with increasing moisture content. Gels made from starch with 70% moisture content treated with RF energy provided the best morphological indicators, including clarity line uniformity and high retention rate. Overall, RF treatment of starch with varying moisture content is an effective method for preparing starch gels for 3D printing.

Inter-Seasonal Estimation of Grass Water Content Indicators Using Multisource Remotely Sensed Data Metrics and the Cloud-Computing Google Earth Engine Platform

Indicators of grass water content (GWC) have a significant impact on eco-hydrological processes such as evapotranspiration and rainfall interception. Several site-specific factors such as seasonal precipitation, temperature, and topographic variations cause soil and ground moisture content variations, which have significant impacts on GWC. Estimating GWC using multisource data may provide robust and accurate predictions, making it a useful tool for plant water quantification and management at various landscape scales. In this study, Sentinel-2 MSI bands, spectral derivatives combined with topographic and climatic variables, were used to estimate leaf area index (LAI), canopy storage capacity (CSC), canopy water content (CWC) and equivalent water thickness (EWT) as indicators of GWC within the communal grasslands in Vulindlela across wet and dry seasons based on single-year data. The results illustrate that the use of combined spectral and topo-climatic variables, coupled with random forest (RF) in the Google Earth Engine (GEE), improved the prediction accuracies of GWC variables across wet and dry seasons. LAI was optimally estimated in the wet season with an RMSE of 0.03 m−2 and R2 of 0.83, comparable to the dry season results, which exhibited an RMSE of 0.04 m−2 and R2 of 0.90. Similarly, CSC was estimated with high accuracy in the wet season (RMSE = 0.01 mm and R2 = 0.86) when compared to the RMSE of 0.03 mm and R2 of 0.93 obtained in the dry season. Meanwhile, for CWC, the wet season results show an RMSE of 19.42 g/m−2 and R2 of 0.76, which were lower than the accuracy of RMSE = 1.35 g/m−2 and R2 = 0.87 obtained in the dry season. Finally, EWT was best estimated in the dry season, yielding a model accuracy of RMSE = 2.01 g/m−2 and R2 = 0.91 as compared to the wet season (RMSE = 10.75 g/m−2 and R2 = 0.65). CSC was best optimally predicted amongst all GWC variables in both seasons. The optimal variables for estimating these GWC variables included the red-edge, near-infrared region (NIR) and short-wave infrared region (SWIR) bands and spectral derivatives, as well as environmental variables such as rainfall and temperature across both seasons. The use of multisource data improved the prediction accuracies for GWC indicators across both seasons. Such information is crucial for rangeland managers in understanding GWC variations across different seasons as well as different ecological gradients.

Numerical Investigation of the Axial Stress Distribution of Self-Tapping Screws in Mass Timber Products during Wetting or Drying

Self-tapping screws (STS) are used in wood-to-wood and wood-to-steel connections in timber structures. Premature failure of STS during the construction phase has been reported by structural engineers and contractors in relation to a few North American mass-timber projects. This STS failure type is suspected of having been precipitated by additional axial stress exerted on STS from swelling of the wood resulting from prolonged wetting. This study investigates the axial stress distribution of STS installed in two mass timber products, cross-laminated timber (CLT) and glulam, under axial loading and changing moisture conditions in the linear elastic regime. The focus is on modelling the stress distribution of STS during wood-wetting. Properties of self-tapping screws under axial loads, such as tensile and withdrawal properties, along with swelling properties of CLT and glulam, have been investigated. A numerical method to predict the axial stress distribution of the screw from these material property tests has been developed. The numerical model has been calibrated with test results. The method developed in this research helps in understanding the premature failure of self-tapping screw connections under the moisture content variation of wood. The next step will be developing an analytical model to predict the axial stress distribution of STS.

Evaluating the use of machine learning for moisture content prediction in base and subgrade layers

Subgrade moisture content significantly influences soil strength and pavement bearing capacity. Pavement moisture content varies greatly throughout the year, especially in cold regions. Thus, having a better understanding of seasonal variation in moisture content in the pavement is needed to be developed. This research aims to apply machine learning models to predict the moisture content of unbound materials in the pavement. Unfrozen volumetric moisture content measurements recorded at the Integrated Road Research Facility test road in Edmonton, Alberta were used to train machine learning models to predict moisture content at depths within 2.7 m of the road surface. Machine learning models were implemented based on three parameters of pavement temperature, day of the year and depth. The results from the machine learning model were compared with a statistical model and showed higher accuracy than the existing model, indicating that machine learning models could enhance moisture content prediction in the pavement.

Diurnal Monitoring of Moisture Content of Scots Pine and Small-Leaved Lime Trunks Using Ground Penetrating Radar (GPR) and Increment Cores

Ground penetrating radar is non-invasive technology suitable for mapping moisture content variations since it shows high sensitivity to changes in water saturation. In this work we used a GPR tomography approach to estimate moisture content within two small-leaved lime (Tilia cordata) and two Scots pine (Pinus sylvestris) trunks. Additional information was derived using the method of GPR zero-offset. GPR data was collected in Moscow (diurnal monitoring in September 2021) using a shielded GPR antenna working at 1500 MHz. Moisture values derived from GPR data were compared with the values obtained directly by measuring sampled wood cores gravimetrically. A good agreement was observed between GPR-derived moisture content and core sample-derived values. Notwithstanding GPR-derived moisture content is about two times higher than core sample-derived values, a strong linear relation with a determination coefficient more than 0.8 is observed. Diurnal monitoring did not reveal any significant changes in moisture content inside the trunks. It can be concluded that the period of early autumn in the Moscow region is characterized by a constant moisture content of the small-leaved lime trunk during the day.

No-tillage with straw mulching promotes wheat production via regulating soil drying-wetting status and reducing soil-air temperature variation at arid regions

Straw returning is a technical measure of crop production widely adopted in arid and water-deficient areas. However, the mechanism by which straw returning drives spatio-temporal changes in soil moisture and temperature to improve crop productivity remains unclear. So, a three-year field experiment was conducted with four various straw returning treatments for wheat production: 1) no-tillage with straw mulching (NTSM), 2) no-tillage with straw standing (NTSS), 3) conventional tillage with straw incorporation (CTS), and 4) conventional tillage without straw returning (CT, control). The spatio-temporal variations of soil moisture content and soil temperature were assessed. It will provide the basis for selecting the appropriate way of straw returning to increase wheat yield and clarifying its hydrothermal regulation mechanism. NTSM and NTSS were effective in maintaining soil moisture and regulating soil temperature, and had a greater effect on grain increase, than CTS and CT. Meanwhile, NTSM had a relatively higher yield than NTSS through better regulation of soil hydrothermal characteristics. NTSM had higher soil moisture content in the 0–120 cm depth by 9.8–10.2%, 6.7–8.2%, 6.5–10.2%, and 6.9–7.4% at sowing to jointing, jointing to booting, booting to early-filling, and early-filling to maturing stages of wheat, respectively. NTSM decreased evapotranspiration modulus coefficient (ETMC) and evapotranspiration intensity (ETI) at jointing to early-filling stage of wheat, but increased both indexes from early-filing to maturing stage of wheat, which is helpful to adjust the contradiction of soil moisture demand for wheat in different growth stages. Additionally, NTSM had 9.8–10.2%, 6.7–8.2%, 6.5–10.2%, and 6.9–7.4% lower soil temperature in the 5–25 cm depth than CT, at the four aforementioned wheat growth stages, respectively. The difference of soil temperature was mainly reflected at the 5–15 cm depth by analyzing the difference on soil temperature in various soil depths. The treatment on NTSM had little variation and stabilized soil temperature, according to the difference between air and average soil temperature of 5–15 cm depth. NTSM allowed wheat to grow a suitable thermal environment across their growth period, which is a significant regulatory mechanism for wheat to maintain better growth and development. Thereby, NTSM boosted wheat grain yield by 18.6–27.3% as compared to CT. Collectively, the NTSM treatment had better effect on regulating soil drying-wetting status and reducing soil-air temperature variation, which could be used as a recommended measure to improve wheat productivity at arid conditions.

Identification of DNA Methylation Changes in European Beech Seeds during Desiccation and Storage.

Ageing and deterioration of seeds is a major problem for the maintenance of seed quality and viability during long-term storage. Prediction of early stages of seed deterioration in order to point out the plantlets' regeneration time is a major challenge of successful storage. In preserved seeds, damages accumulate within cells at the rate mainly related to their moisture content and temperature of storage. Current research reveals global alterations in DNA methylation in lipid-rich intermediate seeds during desiccation and storage at various regimes covering nonoptimal and optimal conditions. We show for the first time that monitoring of 5-methylcytosine (m5C) level in seeds can be used as a truly universal viability marker regardless of postharvest category of seeds and their composition. For seeds stored up to three years, in varied conditions, moisture content, temperature, and time of storage had significant influence on seedling emergence and DNA methylation (p < 0.05). Similarities among lipid-rich intermediate and orthodox seeds regarding different reactions of embryonic axes and cotyledons to desiccation are newly revealed. Along with previous studies on seeds dramatically different in desiccation tolerance (recalcitrant vs. orthodox), results regarding lipid-rich seeds positioned in-between (intermediate) prove that maintaining global DNA methylation status is crucial for maintaining seed viability.

The Role of Drying Schedule and Conditioning in Moisture Uniformity in Wood: A Machine Learning Approach.

Monitoring the moisture content (MC) of wood and avoiding large MC variation is a crucial task as a large moisture spread after drying significantly devalues the product, especially in species with high green MC spread. Therefore, this research aims to optimize kiln-drying and provides a predictive approach to estimate and classify target timber moisture, using a gradient-boosting machine learning model. Inputs include three wood attributes (initial moisture, initial weight, and basic density) and three drying parameters (schedule, conditioning, and post-storage). Results show that initial weight has the highest correlation with the final moisture and possesses the highest relative importance in both predictive and classifier models. This model demonstrated a drop in training accuracy after removing schedule, conditioning, and post-storage from inputs, emphasizing that the drying parameters are significant in the robustness of the model. However, the regression-based model failed to satisfactorily predict the moisture after kiln-drying. In contrast, the classifying model is capable of classifying dried wood into acceptable, over-, and under-dried groups, which could apply to timber pre- and post-sorting. Overall, the gradient-boosting model successfully classified the moisture in kiln-dried western hemlock timber.