Combination of effective color information and machine learning for rapid prediction of soil water content

Soil water content(SWC)is one of the critical indicators in various fields such as geotechnical engineering and agriculture.To avoid the time-consuming,destructive,and laborious drawbacks of conventional SWC measurements,the image-based SWC prediction is considered based on recent advances in quantitative soil color analysis.In this study,a promising method based on the Gaussian-fitting gray histogram is proposed for extracting characteristic parameters by analyzing soil images,aiming to alleviate the interference of complex surface conditions with color information extraction.In addition,an identity matrix consisting of 32 characteristic parameters from eight color spaces is constituted to describe the multi-dimensional information of the soil images.Meanwhile,a subset of 10 parameters is identified through three variable analytical methods.Then,four machine learning models for SWC prediction based on partial least squares regression(PLSR),random forest(RF),support vector machines regression(SVMR),and Gaussian process regression(GPR),are established using 32 and 10 characteristic parameters,and their performance is compared.The results show that the characteristic parameters obtained by Gaussian-fitting can effectively reduce the interference from soil surface conditions.The RGB,CIEXYZ,and CIELCH color spaces and lightness parameters,as the inputs,are more suitable for the SWC prediction models.Furthermore,it is found that 10 parameters could also serve as optimal and generalizable predictors without considerably reducing prediction accuracy,and the GPR model has the best prediction performance(R^(2)≥0.95,RMSE≤2.01%,RPD≥4.95,and RPIQ≥6.37).The proposed image-based SWC predictive models combined with effective color information and machine learning can achieve a transient and highly precise SWC prediction,providing valuable insights for mapping soil moisture fields.

Effect of soaking time of dithionite-citrate-bicarbonate solution on strength and deformation characteristics of lateritic soil

This study aimed to reveal the influence of different free-iron-oxides contents on the strength and deformation characteristics of in situ lateritic soil.A test method that combined the selective chemical dissolution method and in situ Ménard pressuremeter test(PMT)was proposed.The soaking time in dithioniteecitrateebicarbonate(DCB)solution was used as a variable to control the free-iron-oxides content in lateritic soil.Then,the in situ lateritic soil boreholes with different soaking time were tested by PMT.The results showed that the in situ horizontal pressure p0,critical edge pressure pf,ultimate pressure prediction pl,pressuremeter modulus Em,shear modulus Gm,and foundation-bearing capacity f0k of lateritic soil decreased rapidly after immersing in DCB solution within 1e4 d.With increasing soaking time,the decrease rate reduced gradually.Moreover,the relationship curve between free-iron-oxides content and soaking time declined rapidly and then stabilized,and the free-iron-oxides content at the inflection point was 30.11 g/kg.When the free-iron-oxides content changed to the inflection point,the free-iron-oxides that played a cementing role was largely removed,indicating that the effective cementing iron-content of Miaoling lateritic soil was about 52.9%.This study demonstrated that the proposed test method can determine the influence of free-iron-oxides content on the strength and deformation characteristics of lateritic soil.

Resilience and functional redundancy of methanogenic digestion microbiome safeguard recovery of methanogenesis activity under the stress induced by microplastics

Microplastics and nanoplastics are emerging pollutants that substantially influence biological element cycling in natural ecosystems.Plastics are also prevalent in sewage,and they accumulate in waste-activated sludge(WAS).However,the impacts of plastics on the methanogenic digestion of WAS and the underpinning microbiome remain underexplored,particularly during long-term operation.In this study,we found that short-term exposure to individual microplastics and nanoplastics(polyethylene,polyvinyl chloride,polystyrene,and polylactic acid)at a low concentration(10 particles/g sludge)slightly enhanced methanogenesis by 2.1%−9.0%,whereas higher levels(30−200 particles/g sludge)suppressed methanogenesis by 15.2%−30.1%.Notably,the coexistence of multiple plastics,particularly at low concentrations,showed synergistic suppression of methanogenesis.Unexpectedly,methanogenesis activity completely recovered after long-term exposure to plastics,despite obvious suppression of methanogenesis by initial plastic exposure.The inhibition of methanogenesis by plastics could be attributed to the stimulated generation of reactive oxygen species.The stress induced by plastics dramatically decreased the relative abundance of methanogens but showed marginal influence on putative hydrolytic and fermentation populations.Nonetheless,the digestion sludge microbiome exhibited resilience and functional redundancy,contributing to the recovery of methanogenesis during the long-term operation of digesters.Plastics also increased the complexity,modularity,and negative interaction ratios of digestion sludge microbiome networks,but their influence on community assembly varied.Interestingly,a unique plastisphere was observed,the networks and assembly of which were distinct from the sludge microbiome.Collectively,the comprehensive evaluation of the influence of microplastics and nanoplastics on methanogenic digestion,together with the novel ecological insights,contribute to better understanding and manipulating this engineered ecosystem in the face of increasing plastic pollution.