The Effect of Amendment Addition Drill Cuttings On Heavy Metals Accumulation In Soils And Plants: Experimental Study And Arti cial Network Simulation

A greenhouse experiment was carried out to evaluate the influence of drill cuttings addition on the accumulation of heavy metals in soil, in plant biomass (Trifolium pretense L.) cultivated on soils with the addition of this type of waste. The transfer and transformation of heavy metals in the soil with drill cuttings- Trifolium pretense L were discussed. Drilling waste in the amount of 2.5%, 5%, 10% and 15% of dry weight were added to acidic soil. The concentrations of heavy metals in the soil and plant materials were determined by an inductively coupled plasma mass spectrometry method. Results indicated that drilling wastes addition had a positive influence on the growth of Trifolium pretense L. However, the concentrations of heavy metals increased in the prepared mixtures along with the dose of drilling wastes. The drilling wastes addition also changed the metal accumulation capacity in plant parts. Nevertheless, the concentrations of heavy metals in soils and above-ground parts of plants did not exceed the permissible values in respective legal standards. The values of the heavy metals bioconcentration coefficient in Trifolium pretense L at the highest dose of drill cuttings were as follows: in the above-ground parts Cd>Cu>Ni>Cr>Pb>Zn, in roots Cd>Ni>Cr>Zn>Pb>Cu. An artificial neural network model was developed in order to predict the concentration of heavy metals in the plants cultivated on the soils polluted with drill cuttings. The input (drill cuttings dose, pH, organic matter content) and the output data (concentration of heavy metals in the shoot cover) were simulated using an artificial neural network program. The results of this study indicate that an artificial neural network trained for experimental measurements can be successfully employed to rapidly predict the heavy metal content in clover. The artificial neural network achieved coefficients of correlation over 90%.


Introduction
Drill cuttings constitute the spoils obtained in the course of drilling, which is extracted onto the surface along with spent drilling uid. Their composition and amount depend on numerous factors, such as: depth and structure of the well, type of drilled rocks, type of employed drill cuttings and performed actions, as well as the properties of formation water (Abbe et al. 2009). Therefore, the content of chemical compounds in these wastes may vary signi cantly. When considering their impact on the natural environment, the main factors taken into account include the content of heavy metals, inorganic salts, oil derivatives, radionuclides, and colloids. Variability of drilling waste compositions hinders assessing their effect on the environment as well as selecting an optimal method of their management (Ball et al. 2012) The physical and chemical properties of drill cuttings, especially pH (~ 10), high buffer capacity, high content: carbonates, organic matter, and calcium indicate that they may be used for neutralizing acidic soils. However, there are a number of limitations. Drill cuttings contain variable amounts of certain toxic trace elements (e.g., Cd, Cr, Pb, Ni, B and Mo) and high soluble salt (Jamrozik et al. 2015), and this property may affect the the application of drill cuttings (Zvomuya et al. 2011).
It seems that the studies on bioavailability and mobility of heavy metals in the soils with drilling wastes addition are important for assessing the impact of this type of wastes on the environment and the possibility of their addition to soils. As indicated by the studies conducted thus far, the heavy metals contained in drill cuttings occur mainly in the form which is hardly available for living organisms, which is indicated by low percentage of their leaching (Mikos-Szymańska et al. 2018; Cel et al. 2017). In the studies by Zhu et al. (2011) conducted on the drill cuttings containing the residues of oil-based drilling uid, the highest leachability -amounting to 1.61% -was observed in the case of copper, whereas for cadmium and lead it was lower, reaching 0.51% and 0.20%, respectively (Zhu et al. 2011).
Certain researchers (Stuckman et al. 2016) conducted fractionation studies indicating that heavy metals will not be released in signi cant amounts, whereas others observed an increase in the available forms of metals and their mobility in a column study (Bates 1988).
The previous studies on the impact of heavy metals from wastes on soil also differ in terms of the type, amount of added wastes, and the in ltration of metals to soils and plants. McFarland  There are few studies on the bioaccumulation of heavy metals in the plants cultivated on soils with the addition of drilling uids. In this paper, the content of heavy metals in the soils with drilling uid addition and clover cultivated on the prepared mixtures.
Moreover, an arti cial neural network (ANN) model was devised for predicting the concentration of heavy metals in the biomass of clover cultivated on the soils contaminated with drilling wastes. The input data included: the dose of drilling wastes, organic matter content as well as the pH in the soils with drilling wastes addition.
The arti cial neural network models are increasingly often employed for predicting the migration of pollutants in the environment. ANN

Pot experiment:
The studies were conducted on four types of mixtures designated as Z0, Z-2.5, -Z5. Z-10, and Z15, which were prepared based on different proportion of soil and drill cuttings. The share of cuttings in the soil mixture ranged from 2.5-15.0 % by weight, based on the air-dried weight ( Table 1). The soil without addition of drill cuttings were used as a control sample (Z0). The doses were adjusted to be lower than the maximum amount of wastes permitted for sowing, established in Directive 050: drilling waste management. Alberta Energy Resources Conservation Board, Calgary (Directive 50 2016). The tested materials were placed in plastic pots with a capacity of 350 ml and each pot was sown with 12 clover seeds (Trifolium pratense L). The studies were carried out in three replicates for six weeks. The culture was carried out in accordance with the recommendations given in PN-EN ISO 11269-2: 2013-06. The experiment was run under controlled greenhouse conditions at 60% eld water capacity and at 25°C. At the end of the experiment, the plants were harvested and the roots were gently separated from the soil by repeated rinsing. The collected plants were divided into roots and above-ground (shoots) parts. The dry biomass was weighed with an accuracy of 0.01 g.

Soil pH and organic matter percentage in mixtures
The soil pH were measured in 1:5 soil:water suspension in triplicates (1997). In order to calculate the dry weight, the samples were oven-dried for four hours at 105°C to constant weight. The percentage of organic matter (OM, %) was determined according to PN-EN 15935:2013-02 by the combustion of the samples at 500°C for four hours (2013).

Metal concentrations in soils, mixtures, plant biomass and water extract of mixtures
The concentration of Cd, Cr, Cu, Ni, Pb, and Zn in the examined soil and the water extracts of the soil and plant biomass were determined with ICP-OES Ultrace 238 (Jobin Yvon Horriba France) using a direct calibration method. The samples of homogenized soil (1 g) and biomass (0.1 g) were digested in an acid mixture of HNO 3 :HCl (1:3), and the water samples (15 g) were digested in HNO 3 (3 ml) in a microwave system (Multiwave 3000, Anton Paar). The digestion process lasted for 45 min at 180°C and at a pressure of 18 bars.

Results elaboration
Accumulation of particular heavy metals transported from soil to plant was evaluated using the bioconcentration factor (BCF), according to Eq. where LC: is heavy metal concentration in the biomass of shoots (mg kg − 1 ), and RC is heavy metal concentration in the biomass of roots (mg kg − 1 ) (Ociepa 2011).

Statistical analysis
The data were statistically analyzed through parametrical test ANOVA (Tukey's test ) using the Statistica 13.1 software package (Lublin University of Technology license). The letter indicators given at the average value of particular parameters considered in ANOVA test indicate statistically homogeneous groups (Tukey Homogeneous Groups). The presence of the same indicator designates the lack of statistically signi cant difference between them.

Arti cial Neural Network (ANN) model
The obtained experimental data were introduced into the arti cial neural network (ANN) model in order to experimentally verify the concentration of heavy metals in the biomass of clover cultivated on the substrates containing drilling wastes. The input parameters for the model included: drill cuttings dose, pH, and the organic matter content, whereas the concentration of heavy metals in plant shoot was the output neuron (a single neuron in the output layer). Schematic representation of an arti cial neural network for the model is shown in Fig. 1  The pH value is a predominant factor which affects the mobility and bioavailability of heavy metals in soil through governing the solid-solution equilibrium of heavy metals (Zhao and Masaihiko 2007); therefore, the changes of this parameter occurring after waste addition to soil were analyzed. In the conducted studies, the pH of substrates containing wastes increased signi cantly compared to the control sample, ranging from 6.66 to 7.09 and increasing with the drill cuttings dose (Table 2). An increase in pH in the soils following drill

Effects of drill cuttings addition on heavy metal concentrations in soils
Studies showed that drill cuttings addition statistically signi cantly increased the concentration of heavy metals in soil, proportionally to an increased in the share of drill cuttings in mixtures. Cadmium, the concentration of which did not increase following waste addition, and even slightly reduced instead, constituted an exception (Fig. 2).
The highest content of each heavy metal was found in the mixture containing 15% drill cuttings. However, even in this mixture, the content of one of the analyzed heavy metals did not exceed the limit concentrations stated in the Polish law for class II soils, which include agricultural lands (2016), which amount to: for Cd -2 mg/kg; Cr -150-500 mg/kg; Cu and Ni 100-300 mg/kg; Pb 100-500 mg/kg; Zn 300-1000 mg/kg.

Effects of drill cuttings addition on plant growth and heavy metals accumulation and translocation in red clover biomass
Changes in the substrate conditions caused by the introduction of drilling wastes to acidic soil, affected the amount and chemical composition of the test plant -red clover (Trifolium pretense) (Fig. 3).
The highest amount of clover biomass was obtained in the case of a mixture with 5% drilling wastes addition; it was 2.5-fold higher in comparison with the control soil. The biomass of clover cultivated on the mixtures with 5% and 10% drill cuttings addition reached twice higher values, whereas on the mixtures with 15% drill cuttings addition, it was 1.5-fold greater than the biomass cultivated on the control soil. Tukey's test indicated no statistically signi cant differences between the mass of clover roots cultivated on particular mixtures. However, differentiation occurred in the biomass of clover shoots (Kujawska and Pawłowska, 2020). The heavy metal concentration in the shoots of clover cultivated on the investigated mixtures was determined and the results are shown in Fig. 4.
The drilling wastes addition statistically signi cantly increased the content of cadmium and copper, whereas it reduced the content of Cr and Pb in clover shoots. No statistically signi cant changes in the concentrations of nickel and zinc in clover shoots cultivated on the non-modi ed soil and the soil with drilling wastes addition were observed. The increasing concentrations of these elements in biomass can be attributed to a change in the pH of the substrate, which affected the mobility and bioavailability of these elements (Kgopa et al. 2017). The mobility of these elements increases already at pH 6-6.5 values, slightly acidic and very slightly alkaline, which characterized the prepared mixtures. These values are within the range measured by Reeves and Baker (2000) for plants growing in metalliferous soils (5-25 mg kg − 1 ) (Reeves and Baker 2000). Cadmium is the most mobile and easily soluble heavy metal (Akhter et al. 2014).
Although drill cuttings did not signi cantly increase the concentration of cadmium in substrates, the clover cultivated on these substrates took up cadmium easily.
The In the case of roots, it was observed that the drill cuttings addition statistically signi cantly increased the clover capacity for Zn and Ni accumulation in all mixtures. Moreover, statistically signi cant increase of Cd accumulation in clover roots was observed, but only for the highest, 15% drill cuttings dose. However, the values of BCF for Cd were the highest, compared to other metals, and in all collected plants, the BCF value of this element was higher than 2. Such high bioconcentration factor was observed only in the case of Pb on the control sample. In turn, the BCF values higher than 1 were observed in root biomass in the case of Ni in the plants cultivated on the substrates containing drill cuttings (Fig. 6). It was observed that clover roots accumulated (0.48-0.52), Pb (0.20-0.45), Cu (0.16-0.19) i Zn (0.29-0.34) to a moderate degree.
It was observed that the drill cuttings addition to the substrate changed the metal accumulation capacity in particular plant parts. The accumulation of metals in the below-ground parts of plants cultivated on the control soil can be presented in the following order: Cd > Ni > Pb > Zn > Cr > Cu, whereas in roots, it is slightly different: Pb > Cd > Cr > Ni > Cu > Zn. After the highest drill cuttings addition the order was as follows: Cd > Cu > Ni > Cr > Pb > Zn in the above-ground parts and Cd > Ni > Cr > Zn > Pb > Cu in roots.
Accumulation of the investigated elements in clover roots was much higher than in the above-ground parts, which indicates the usefulness of this species in phytostabilization of polluted soils. In addition, introduction of 5% drill cuttings improved the growth conditions, which increased the accumulation of metals in roots and reduced their transport to the above-ground parts, which is especially evident in the case of cadmium, nickel, and zinc.
Although BCF can be a useful tool for assessing the in uence of waste addition to soil on the accumulation of elements in biomass; however, interpretation of the obtained results is not easy, since bioaccumulation of metal by plants is dependent upon numerous factors, including variable soil conditions. As it was observed by McGrath and Zhao (2003), the values of BCF generally decrease with increasing metal concentration in soil (McGrath and Zhao 2003).
The obtained translocation factor (mobility) values of heavy metals in the clover cultivated on the mixtures with drilling wastes addition decreased under their in uence ( Table 3). All the determined TF values were lower than 1; hence, the mobility of metals in the root-above-ground part system of clover was very low. The reason for lower translocation of metals in the substrates containing drill cuttings might be alkalinization, which causes retention of metals in the root system. This phenomenon was also described by Kumpiene

Arti cial Neural Networks
On the basis of the experimental data: drilling waste doses, pH, organic matter of the mixtures with drill uids, 100 networks were developed. The network quality was assessed using the following indicators: quality of training, quality of validation, training error and validation error from the least squares method, in order to select the most appropriate network type -MLP or RBF. The obtained network parameters were presented in Table 5.  Regression coe cients (R) for selected networks for training, validation, and test data assume the values over 90%. Such high regression coe cients indicate good t of the network. As it was presented in Table 5, mean coe cients of correlation between the experimentally determined concentrations of heavy metals in plants and the values predicted by ANN reached were higher than 95%, which indicates that the ANN model was able to quickly and reliably predict the concentrations of heavy metals. Low values of errors (< 0.1) also prove high accuracy of neural networks.
In order to investigate the in uence of drill cuttings addition, pH, and organic matter content of soil on the concentration of heavy metals, a sensitivity analysis (Table 6) was carried out. The network sensitivity analysis indicated the highest sensitivity to the impact of drill cuttings addition on the concentration of heavy metals in plants. On the basis of the obtained experimental results, an arti cial neural network model for predicting the metal concentrations in plants. Such models can be created using various soil additives and soil quality parameters, which facilitates predicting the impact of wastes on the accumulation of metals in plants.
The results obtained by us and other researchers showed that ANN can be employed for Gharaibeh and Ben-Hani (2003) created an arti cial neural network model for predicting phytotoxicity, dry mass accumulation and reduction depending on the concentrations of metals used for irrigation. The input (selenium and nitrate levels) and the output data (growth reduction and selenium bio-tissues uptake) were simulated using arti cial neural network program. Simulated data was then used to predict the interaction between selenium and nitrate in irrigation water at different levels of both nitrates and selenium (Gharaibeh and Bani-Hani 2003).
The versatility of arti cial neural network tools is the feature, which enables to account for the selected quantity and quality of the investigated soil quality parameters. Moreover, arti cial neural network models may be the basic tool for managers, engineers, and decision makers, aiding in designing, managing, and making decisions pertaining to the introduction of additives to soil.

Conclusions
1. Drill cuttings addition to acidic soil (pH ∼4.2) signi cantly increased the concentration of heavy metals (excluding cadmium). However, the concentrations of these metals did not exceed the permissible values established in the regulations related to the quality fo agricultural lands. 3. Heavy metals were accumulated in higher concentrations in the roots of red clover than in the aboveground parts. This observation is of practical importance, because clover is commonly used as animal forage. Shoots of the clover cultivated on the mixtures with wastes indicated hyperaccumulation of cadmium and nickel as well as moderate accumulation of chromium, lead, copper, and zinc.
4. Drilling wastes reduced the mobility of heavy metals in the root-shoot system. 5. The performed experimental studies showed the potential of developing the models for predicting the heavy metal concentrations in plants, based on arti cial neural networks. This is proven by a good quality of the networks determined on the basis of high coe cient of correlation (> 0.99). The sensitivity analysis of the developed networks showed that the drilling wastes addition had the highest impact on the heavy metal content in plants, in comparison to the changes in pH and organic matter content.
6. Undoubtedly, the impact of pollutants contained in drill cuttings requires constant monitoring; therefore, it seems justi ed to include model studies, in addition to experimental studies.

Declarations
Ethical approval The experiments comply with the current laws of Poland.
Compliance with ethical standards Heavy metals concentration in the shoot biomass obtained in the experiment Bioconcentration factors (BCF) of the examined metals in the red clover shoots Bioconcentration factors (BCF) of the examined metals in the clover roots