对下面的数据进行拟合，生成对应的matlab代码x坐标 y坐标 某时刻污染物浓度 14.6 24.12 10.5272 21.58 56.09 11.2960 0.77 53.31 9.9625 49.2 43.13 10.8033 8.36 55.85 10.9152 5.31 53.32 10.4919 18.62 14.25 10.4518 9.91 10.24 8.9304 24.48 79.93 9.5115 16.97 13.69 10.1678 47.58 2.61 10.2770 46.02 44.9 10.9207 2.63 70.55 10.5062 36.89 53.53 10.7704 13.46 15.23 9.8156 21.14 29.51 11.5348 27.39 36.86 11.9530 47.14 78.53 7.7559 20.89 12.51 10.6018 49.15 68.44 8.4879

可以使用多项式回归进行拟合，以下是对应的 Matlab 代码：

% 输入数据
x = [14.6, 21.58, 0.77, 49.2, 8.36, 5.31, 18.62, 9.91, 24.48, 16.97, 47.58, 46.02, 2.63, 36.89, 13.46, 21.14, 27.39, 47.14, 20.89, 49.15];
y = [24.12, 56.09, 53.31, 43.13, 55.85, 53.32, 14.25, 10.24, 79.93, 13.69, 2.61, 44.9, 70.55, 53.53, 15.23, 29.51, 36.86, 78.53, 12.51, 68.44];
z = [10.5272, 11.2960, 9.9625, 10.8033, 10.9152, 10.4919, 10.4518, 8.9304, 9.5115, 10.1678, 10.2770, 10.9207, 10.5062, 10.7704, 9.8156, 11.5348, 11.9530, 7.7559, 10.6018, 8.4879];

% 多项式回归拟合
p = polyfitn([x' y'], z', 2);

% 生成网格数据
[X,Y] = meshgrid(min(x):0.1:max(x), min(y):0.1:max(y));

% 计算拟合值
Z = polyvaln(p, [X(:) Y(:)]);

% 绘制拟合结果
figure;
scatter3(x, y, z, 'filled');
hold on;
surf(X, Y, reshape(Z, size(X)), 'FaceAlpha', 0.5);
xlabel('x');
ylabel('y');
zlabel('pollutant concentration');
title('Polynomial Regression Fitting');

运行以上代码，会得到一个带有散点和拟合面的三维图形，其中散点是输入的数据，拟合面是通过多项式回归拟合得到的结果。你可以根据实际需求调整多项式的阶数和网格的密度来得到更精细的拟合效果。